Video-Classification.md

Video Classification

Title	Date	Abstract	Comment	CodeRepository
vAccSOL: Efficient and Transparent AI Vision Offloading for Mobile Robots	2026-03-17	Show Mobile robots are increasingly deployed for inspection, patrol, and search-and-rescue operations, relying on computer vision for perception, navigation, and autonomous decision-making. However, executing modern vision workloads onboard is challenging due to limited compute resources and strict energy constraints. While some platforms include embedded accelerators, these are typically tied to proprietary software stacks, leaving user-defined workloads to run on resource-constrained companion computers. We present vAccSOL, a framework for efficient and transparent execution of AI-based vision workloads across heterogeneous robotic and edge platforms. vAccSOL integrates two components: SOL, a neural network compiler that generates optimized inference libraries with minimal runtime dependencies, and vAccel, a lightweight execution framework that transparently dispatches inference locally on the robot or to nearby edge infrastructure. This combination enables hardware-optimized inference and flexible execution placement without requiring modifications to robot applications. We evaluate vAccSOL on a real-world testbed with a commercial quadruped robot and twelve deep learning models covering image classification, video classification, and semantic segmentation. Compared to a PyTorch compiler baseline, SOL achieves comparable or better inference performance. With edge offloading, vAccSOL reduces robot-side power consumption by up to 80% and edge-side power by up to 60% compared to PyTorch, while increasing vision pipeline frame rate by up to 24x, extending the operating lifetime of battery-powered robots.		None
HSEmotion Team at ABAW-10 Competition: Facial Expression Recognition, Valence-Arousal Estimation, Action Unit Detection and Fine-Grained Violence Classification	2026-03-13	Show This article presents our results for the 10th Affective Behavior Analysis in-the-Wild (ABAW) competition. For frame-wise facial emotion understanding tasks (frame-wise facial expression recognition, valence-arousal estimation, action unit detection), we propose a fast approach based on facial embedding extraction with pre-trained EfficientNet-based emotion recognition models. If the latter model's confidence exceeds a threshold, its prediction is used. Otherwise, we feed embeddings into a simple multi-layered perceptron trained on the AffWild2 dataset. Estimated class-level scores are smoothed in a sliding window of fixed size to mitigate noise in frame-wise predictions. For the fine-grained violence detection task, we examine several pre-trained architectures for frame embeddings and their aggregation for video classification. Experimental results on four tasks from the ABAW challenge demonstrate that our approach significantly improves validation metrics over existing baselines.	to be... to be submitted to ABAW-10 workshop of CVPR 2026	None
Contrastive learning-based video quality assessment-jointed video vision transformer for video recognition	2026-03-11	Show Video quality significantly affects video classification. We found this problem when we classified Mild Cognitive Impairment well from clear videos, but worse from blurred ones. From then, we realized that referring to Video Quality Assessment (VQA) may improve video classification. This paper proposed Self-Supervised Learning-based Video Vision Transformer combined with No-reference VQA for video classification (SSL-V3) to fulfill the goal. SSL-V3 leverages Combined-SSL mechanism to join VQA into video classification and address the label shortage of VQA, which commonly occurs in video datasets, making it impossible to provide an accurate Video Quality Score. In brief, Combined-SSL takes video quality score as a factor to directly tune the feature map of the video classification. Then, the score, as an intersected point, links VQA and classification, using the supervised classification task to tune the parameters of VQA. SSL-V3 achieved robust experimental results on two datasets. For example, it reached an accuracy of 94.87% on some interview videos in the I-CONECT (a facial video-involved healthcare dataset), verifying SSL-V3's effectiveness.	9 fig... 9 figures, 10 tables,	None
From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification	2026-03-11	Show Conventional video classification models, acting as effective imitators, excel in scenarios with homogeneous data distributions. However, real-world applications often present an open-instance challenge, where intra-class variations are vast and complex, beyond existing benchmarks. While traditional video encoder models struggle to fit these diverse distributions, vision-language models (VLMs) offer superior generalization but have not fully leveraged their reasoning capabilities (intuition) for such tasks. In this paper, we bridge this gap with an intrinsic reasoning framework that evolves open-instance video classification from imitation to intuition. Our approach, namely DeepIntuit, begins with a cold-start supervised alignment to initialize reasoning capability, followed by refinement using Group Relative Policy Optimization (GRPO) to enhance reasoning coherence through reinforcement learning. Crucially, to translate this reasoning into accurate classification, DeepIntuit then introduces an intuitive calibration stage. In this stage, a classifier is trained on this intrinsic reasoning traces generated by the refined VLM, ensuring stable knowledge transfer without distribution mismatch. Extensive experiments demonstrate that for open-instance video classification, DeepIntuit benefits significantly from transcending simple feature imitation and evolving toward intrinsic reasoning. Our project is available at https://bwgzk-keke.github.io/DeepIntuit/.	18 pages, 7 figures	Code Link
OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection	2026-02-27	Show Visual fall detection models trained on small, staged datasets have unclear real-world utility due to limited diversity and inconsistent evaluation protocols. We present OmniFall, a unified benchmark with 80 hours / 15k videos and dense frame-level annotations in a harmonized 16-class taxonomy, spanning three complementary domains: OF-Staged (eight public staged sets, standardized with cross-subject/view splits), OF-Synthetic (12k videos, 17 h; controlled diversity in age, body type, environment, camera), and OF-In-the-Wild (the first test-only benchmark curated from genuine accident videos). OmniFall supports both video classification and timeline segmentation, and its cross-domain protocol isolates staged/synthetic-to-wild generalization. Our results show that carefully designed synthetic data can match or surpass real staged footage on cross-domain transfer, while reducing privacy risk and easing data collection. By combining privacy-amenable synthetic/staged sources with a public, test-only wild target and releasing dense, standardized timelines, OmniFall provides a comprehensive benchmark for privacy-preserving fall detection and fall-related (pre/post-fall) segmentation, enabling robust detectors that generalize to uncontrolled environments. Project page: http://simplexsigil.github.io/omnifall/		Code Link
Assessing Situational and Spatial Awareness of VLMs with Synthetically Generated Video	2026-01-22	Show Spatial reasoning in vision language models (VLMs) remains fragile when semantics hinge on subtle temporal or geometric cues. We introduce a synthetic benchmark that probes two complementary skills: situational awareness (recognizing whether an interaction is harmful or benign) and spatial awareness (tracking who does what to whom, and reasoning about relative positions and motion). Through minimal video pairs, we test three challenges: distinguishing violence from benign activity, binding assailant roles across viewpoints, and judging fine-grained trajectory alignment. While we evaluate recent VLMs in a training-free setting, the benchmark is applicable to any video classification model. Results show performance only slightly above chance across tasks. A simple aid, stable color cues, partly reduces assailant role confusions but does not resolve the underlying weakness. By releasing data and code, we aim to provide reproducible diagnostics and seed exploration of lightweight spatial priors to complement large-scale pretraining.		None
Not all Blends are Equal: The BLEMORE Dataset of Blended Emotion Expressions with Relative Salience Annotations	2026-01-19	Show Humans often experience not just a single basic emotion at a time, but rather a blend of several emotions with varying salience. Despite the importance of such blended emotions, most video-based emotion recognition approaches are designed to recognize single emotions only. The few approaches that have attempted to recognize blended emotions typically cannot assess the relative salience of the emotions within a blend. This limitation largely stems from the lack of datasets containing a substantial number of blended emotion samples annotated with relative salience. To address this shortcoming, we introduce BLEMORE, a novel dataset for multimodal (video, audio) blended emotion recognition that includes information on the relative salience of each emotion within a blend. BLEMORE comprises over 3,000 clips from 58 actors, performing 6 basic emotions and 10 distinct blends, where each blend has 3 different salience configurations (50/50, 70/30, and 30/70). Using this dataset, we conduct extensive evaluations of state-of-the-art video classification approaches on two blended emotion prediction tasks: (1) predicting the presence of emotions in a given sample, and (2) predicting the relative salience of emotions in a blend. Our results show that unimodal classifiers achieve up to 29% presence accuracy and 13% salience accuracy on the validation set, while multimodal methods yield clear improvements, with ImageBind + WavLM reaching 35% presence accuracy and HiCMAE 18% salience accuracy. On the held-out test set, the best models achieve 33% presence accuracy (VideoMAEv2 + HuBERT) and 18% salience accuracy (HiCMAE). In sum, the BLEMORE dataset provides a valuable resource to advancing research on emotion recognition systems that account for the complexity and significance of blended emotion expressions.	Accep... Accepted for publication at IEEE Face & Gesture 2026	None
Effects of Different Attention Mechanisms Applied on 3D Models in Video Classification	2026-01-15	Show Human action recognition has become an important research focus in computer vision due to the wide range of applications where it is used. 3D Resnet-based CNN models, particularly MC3, R3D, and R(2+1)D, have different convolutional filters to extract spatiotemporal features. This paper investigates the impact of reducing the captured knowledge from temporal data, while increasing the resolution of the frames. To establish this experiment, we created similar designs to the three originals, but with a dropout layer added before the final classifier. Secondly, we then developed ten new versions for each one of these three designs. The variants include special attention blocks within their architecture, such as convolutional block attention module (CBAM), temporal convolution networks (TCN), in addition to multi-headed and channel attention mechanisms. The purpose behind that is to observe the extent of the influence each of these blocks has on performance for the restricted-temporal models. The results of testing all the models on UCF101 have shown accuracy of 88.98% for the variant with multiheaded attention added to the modified R(2+1)D. This paper concludes the significance of missing temporal features in the performance of the newly created increased resolution models. The variants had different behavior on class-level accuracy, despite the similarity of their enhancements to the overall performance.	18 pa... 18 pages, 6 figures, conference	None
Cell Behavior Video Classification Challenge, a benchmark for computer vision methods in time-lapse microscopy	2026-01-15	Show The classification of microscopy videos capturing complex cellular behaviors is crucial for understanding and quantifying the dynamics of biological processes over time. However, it remains a frontier in computer vision, requiring approaches that effectively model the shape and motion of objects without rigid boundaries, extract hierarchical spatiotemporal features from entire image sequences rather than static frames, and account for multiple objects within the field of view. To this end, we organized the Cell Behavior Video Classification Challenge (CBVCC), benchmarking 35 methods based on three approaches: classification of tracking-derived features, end-to-end deep learning architectures to directly learn spatiotemporal features from the entire video sequence without explicit cell tracking, or ensembling tracking-derived with image-derived features. We discuss the results achieved by the participants and compare the potential and limitations of each approach, serving as a basis to foster the development of computer vision methods for studying cellular dynamics.		None
Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices	2026-01-11	Show Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label sparsity, temporal continuity, and label co-occurrence that can be leveraged for more efficient inference. We introduce Polymorph, a context-aware framework that activates a minimal set of lightweight Low Rank Adapters (LoRA) per frame. Each adapter specializes in a subset of classes derived from co-occurrence patterns and is implemented as a LoRA weight over a shared backbone. At runtime, Polymorph dynamically selects and composes only the adapters needed to cover the active labels, avoiding full-model switching and weight merging. This modular strategy improves scalability while reducing latency and energy overhead. Polymorph achieves 40% lower energy consumption and improves mAP by 9 points over strong baselines on the TAO dataset. Polymorph is open source at https://github.com/inference-serving/polymorph/.	Accep... Accepted at the IEEE/CVF winter conference on applications of computer vision (WACV 2026)	Code Link
GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection	2025-12-23	Show The rapid advancement of video generation models has made it increasingly challenging to distinguish AI-generated videos from real ones. This issue underscores the urgent need for effective AI-generated video detectors to prevent the dissemination of false information via such videos. However, the development of high-performance AI-generated video detectors is currently impeded by the lack of large-scale, high-quality datasets specifically designed for generative video detection. To this end, we introduce GenVidBench, a challenging AI-generated video detection dataset with several key advantages: 1) Large-scale video collection: The dataset contains 6.78 million videos and is currently the largest dataset for AI-generated video detection. 2) Cross-Source and Cross-Generator: The cross-source generation reduces the interference of video content on the detection. The cross-generator ensures diversity in video attributes between the training and test sets, preventing them from being overly similar. 3) State-of-the-Art Video Generators: The dataset includes videos from 11 state-of-the-art AI video generators, ensuring that it covers the latest advancements in the field of video generation. These generators ensure that the datasets are not only large in scale but also diverse, aiding in the development of generalized and effective detection models. Additionally, we present extensive experimental results with advanced video classification models. With GenVidBench, researchers can efficiently develop and evaluate AI-generated video detection models.. Datasets and code are available at https://genvidbench.github.io.	AAAI 2026	None
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language	2025-12-11	Show We introduce VL-JEPA, a vision-language model built on a Joint Embedding Predictive Architecture (JEPA). Instead of autoregressively generating tokens as in classical VLMs, VL-JEPA predicts continuous embeddings of the target texts. By learning in an abstract representation space, the model focuses on task-relevant semantics while abstracting away surface-level linguistic variability. In a strictly controlled comparison against standard token-space VLM training with the same vision encoder and training data, VL-JEPA achieves stronger performance while having 50% fewer trainable parameters. At inference time, a lightweight text decoder is invoked only when needed to translate VL-JEPA predicted embeddings into text. We show that VL-JEPA natively supports selective decoding that reduces the number of decoding operations by 2.85x while maintaining similar performance compared to non-adaptive uniform decoding. Beyond generation, the VL-JEPA's embedding space naturally supports open-vocabulary classification, text-to-video retrieval, and discriminative VQA without any architecture modification. On eight video classification and eight video retrieval datasets, the average performance VL-JEPA surpasses that of CLIP, SigLIP2, and Perception Encoder. At the same time, the model achieves comparable performance as classical VLMs (InstructBLIP, QwenVL) on four VQA datasets: GQA, TallyQA, POPE and POPEv2, despite only having 1.6B parameters.		None
VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generation	2025-12-05	Show Spatio-temporal scene graph generation (ST-SGG) aims to model objects and their evolving relationships across video frames, enabling interpretable representations for downstream reasoning tasks such as video captioning and visual question answering. Despite recent advancements in DETR-style single-stage ST-SGG models, they still suffer from several key limitations. First, while these models rely on attention-based learnable queries as a core component, these learnable queries are semantically uninformed and instance-agnostically initialized. Second, these models rely exclusively on unimodal visual features for predicate classification. To address these challenges, we propose VOST-SGG, a VLM-aided one-stage ST-SGG framework that integrates the common sense reasoning capabilities of vision-language models (VLMs) into the ST-SGG pipeline. First, we introduce the dual-source query initialization strategy that disentangles what to attend to from where to attend, enabling semantically grounded what-where reasoning. Furthermore, we propose a multi-modal feature bank that fuses visual, textual, and spatial cues derived from VLMs for improved predicate classification. Extensive experiments on the Action Genome dataset demonstrate that our approach achieves state-of-the-art performance, validating the effectiveness of integrating VLM-aided semantic priors and multi-modal features for ST-SGG. We will release the code at https://github.com/LUNAProject22/VOST.		Code Link
Detection of Intoxicated Individuals from Facial Video Sequences via a Recurrent Fusion Model	2025-12-04	Show Alcohol consumption is a significant public health concern and a major cause of accidents and fatalities worldwide. This study introduces a novel video-based facial sequence analysis approach dedicated to the detection of alcohol intoxication. The method integrates facial landmark analysis via a Graph Attention Network (GAT) with spatiotemporal visual features extracted using a 3D ResNet. These features are dynamically fused with adaptive prioritization to enhance classification performance. Additionally, we introduce a curated dataset comprising 3,542 video segments derived from 202 individuals to support training and evaluation. Our model is compared against two baselines: a custom 3D-CNN and a VGGFace+LSTM architecture. Experimental results show that our approach achieves 95.82% accuracy, 0.977 precision, and 0.97 recall, outperforming prior methods. The findings demonstrate the model's potential for practical deployment in public safety systems for non-invasive, reliable alcohol intoxication detection.		None
Classification of User Satisfaction in HRI with Social Signals in the Wild	2025-12-03	Show Socially interactive agents (SIAs) are being used in various scenarios and are nearing productive deployment. Evaluating user satisfaction with SIAs' performance is a key factor in designing the interaction between the user and SIA. Currently, subjective user satisfaction is primarily assessed manually through questionnaires or indirectly via system metrics. This study examines the automatic classification of user satisfaction through analysis of social signals, aiming to enhance both manual and autonomous evaluation methods for SIAs. During a field trial at the Deutsches Museum Bonn, a Furhat Robotics head was employed as a service and information hub, collecting an "in-the-wild" dataset. This dataset comprises 46 single-user interactions, including questionnaire responses and video data. Our method focuses on automatically classifying user satisfaction based on time series classification. We use time series of social signal metrics derived from the body pose, time series of facial expressions, and physical distance. This study compares three feature engineering approaches on different machine learning models. The results confirm the method's effectiveness in reliably identifying interactions with low user satisfaction without the need for manually annotated datasets. This approach offers significant potential for enhancing SIA performance and user experience through automated feedback mechanisms.	15 pa... 15 pages, 3 figures. This paper has been accepted for publication at ICSR+AI 2025	None
Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching	2025-12-03	Show Content moderation remains a critical yet challenging task for large-scale user-generated video platforms, especially in livestreaming environments where moderation must be timely, multimodal, and robust to evolving forms of unwanted content. We present a hybrid moderation framework deployed at production scale that combines supervised classification for known violations with reference-based similarity matching for novel or subtle cases. This hybrid design enables robust detection of both explicit violations and novel edge cases that evade traditional classifiers. Multimodal inputs (text, audio, visual) are processed through both pipelines, with a multimodal large language model (MLLM) distilling knowledge into each to boost accuracy while keeping inference lightweight. In production, the classification pipeline achieves 67% recall at 80% precision, and the similarity pipeline achieves 76% recall at 80% precision. Large-scale A/B tests show a 6-8% reduction in user views of unwanted livestreams}. These results demonstrate a scalable and adaptable approach to multimodal content governance, capable of addressing both explicit violations and emerging adversarial behaviors.	Accepted at KDD 2026	None
OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning	2025-12-02	Show Omni-modal Large Language Models (OLLMs) that process text, images, videos, and audio introduce new challenges for safety and value guardrails in human-AI interaction. Prior guardrail research largely targets unimodal settings and typically frames safeguarding as binary classification, which limits robustness across diverse modalities and tasks. To address this gap, we propose OmniGuard, the first family of omni-modal guardrails that performs safeguarding across all modalities with deliberate reasoning ability. To support the training of OMNIGUARD, we curate a large, comprehensive omni-modal safety dataset comprising over 210K diverse samples, with inputs that cover all modalities through both unimodal and cross-modal samples. Each sample is annotated with structured safety labels and carefully curated safety critiques from expert models through targeted distillation. Extensive experiments on 15 benchmarks show that OmniGuard achieves strong effectiveness and generalization across a wide range of multimodal safety scenarios. Importantly, OmniGuard provides a unified framework that enforces policies and mitigates risks in omni-modalities, paving the way toward building more robust and capable omnimodal safeguarding systems.		None
Evaluating SAM2 for Video Semantic Segmentation	2025-12-01	Show The Segmentation Anything Model 2 (SAM2) has proven to be a powerful foundation model for promptable visual object segmentation in both images and videos, capable of storing object-aware memories and transferring them temporally through memory blocks. While SAM2 excels in video object segmentation by providing dense segmentation masks based on prompts, extending it to dense Video Semantic Segmentation (VSS) poses challenges due to the need for spatial accuracy, temporal consistency, and the ability to track multiple objects with complex boundaries and varying scales. This paper explores the extension of SAM2 for VSS, focusing on two primary approaches and highlighting firsthand observations and common challenges faced during this process. The first approach involves using SAM2 to extract unique objects as masks from a given image, with a segmentation network employed in parallel to generate and refine initial predictions. The second approach utilizes the predicted masks to extract unique feature vectors, which are then fed into a simple network for classification. The resulting classifications and masks are subsequently combined to produce the final segmentation. Our experiments suggest that leveraging SAM2 enhances overall performance in VSS, primarily due to its precise predictions of object boundaries.	17 pa... 17 pages, 3 figures and 7 tables	None
OmniFD: A Unified Model for Versatile Face Forgery Detection	2025-11-30	Show Face forgery detection encompasses multiple critical tasks, including identifying forged images and videos and localizing manipulated regions and temporal segments. Current approaches typically employ task-specific models with independent architectures, leading to computational redundancy and ignoring potential correlations across related tasks. We introduce OmniFD, a unified framework that jointly addresses four core face forgery detection tasks within a single model, i.e., image and video classification, spatial localization, and temporal localization. Our architecture consists of three principal components: (1) a shared Swin Transformer encoder that extracts unified 4D spatiotemporal representations from both images and video inputs, (2) a cross-task interaction module with learnable queries that dynamically captures inter-task dependencies through attention-based reasoning, and (3) lightweight decoding heads that transform refined representations into corresponding predictions for all FFD tasks. Extensive experiments demonstrate OmniFD's advantage over task-specific models. Its unified design leverages multi-task learning to capture generalized representations across tasks, especially enabling fine-grained knowledge transfer that facilitates other tasks. For example, video classification accuracy improves by 4.63% when image data are incorporated. Furthermore, by unifying images, videos and the four tasks within one framework, OmniFD achieves superior performance across diverse benchmarks with high efficiency and scalability, e.g., reducing 63% model parameters and 50% training time. It establishes a practical and generalizable solution for comprehensive face forgery detection in real-world applications. The source code is made available at https://github.com/haotianll/OmniFD.		Code Link
Sign Language Recognition using Bidirectional Reservoir Computing	2025-11-30	Show Sign language recognition (SLR) facilitates communication between deaf and hearing individuals. Deep learning is widely used to develop SLR-based systems; however, it is computationally intensive and requires substantial computational resources, making it unsuitable for resource-constrained devices. To address this, we propose an efficient sign language recognition system using MediaPipe and an echo state network (ESN)-based bidirectional reservoir computing (BRC) architecture. MediaPipe extracts hand joint coordinates, which serve as inputs to the ESN-based BRC architecture. The BRC processes these features in both forward and backward directions, efficiently capturing temporal dependencies. The resulting states of BRC are concatenated to form a robust representation for classification. We evaluated our method on the Word-Level American Sign Language (WLASL) video dataset, achieving a competitive accuracy of 57.71% and a significantly lower training time of only 9 seconds, in contrast to the 55 minutes and $38$ seconds required by the deep learning-based Bi-GRU approach. Consequently, the BRC-based SLR system is well-suited for edge devices.		None
DisMo: Disentangled Motion Representations for Open-World Motion Transfer	2025-11-28	Show Recent advances in text-to-video (T2V) and image-to-video (I2V) models, have enabled the creation of visually compelling and dynamic videos from simple textual descriptions or initial frames. However, these models often fail to provide an explicit representation of motion separate from content, limiting their applicability for content creators. To address this gap, we propose DisMo, a novel paradigm for learning abstract motion representations directly from raw video data via an image-space reconstruction objective. Our representation is generic and independent of static information such as appearance, object identity, or pose. This enables open-world motion transfer, allowing motion to be transferred across semantically unrelated entities without requiring object correspondences, even between vastly different categories. Unlike prior methods, which trade off motion fidelity and prompt adherence, are overfitting to source structure or drifting from the described action, our approach disentangles motion semantics from appearance, enabling accurate transfer and faithful conditioning. Furthermore, our motion representation can be combined with any existing video generator via lightweight adapters, allowing us to effortlessly benefit from future advancements in video models. We demonstrate the effectiveness of our method through a diverse set of motion transfer tasks. Finally, we show that the learned representations are well-suited for downstream motion understanding tasks, consistently outperforming state-of-the-art video representation models such as V-JEPA in zero-shot action classification on benchmarks including Something-Something v2 and Jester. Project page: https://compvis.github.io/DisMo	Accep... Accepted at NeurIPS 2025	Code Link
Source-free Video Domain Adaptation by Learning from Noisy Labels	2025-11-28	Show Despite the progress seen in classification methods, current approaches for handling videos with distribution shifts in source and target domains remain source-dependent as they require access to the source data during the adaptation stage. In this paper, we present a self-training based source-free video domain adaptation approach to address this challenge by bridging the gap between the source and the target domains. We use the source pre-trained model to generate pseudo-labels for the target domain samples, which are inevitably noisy. Thus, we treat the problem of source-free video domain adaptation as learning from noisy labels and argue that the samples with correct pseudo-labels can help us in adaptation. To this end, we leverage the cross-entropy loss as an indicator of the correctness of the pseudo-labels and use the resulting small-loss samples from the target domain for fine-tuning the model. We further enhance the adaptation performance by implementing a teacher-student (TS) framework, in which the teacher, which is updated gradually, produces reliable pseudo-labels. Meanwhile, the student undergoes fine-tuning on the target domain videos using these generated pseudo-labels to improve its performance. Extensive experimental evaluations show that our methods, termed as CleanAdapt, CleanAdapt + TS, achieve state-of-the-art results, outperforming the existing approaches on various open datasets. Our source code is publicly available at https://avijit9.github.io/CleanAdapt.	Our e... Our extended ICVGIP paper is now accepted in Pattern Recognition	Code Link
CNN-Based Framework for Pedestrian Age and Gender Classification Using Far-View Surveillance in Mixed-Traffic Intersections	2025-11-28	Show Pedestrian safety remains a pressing concern in congested urban intersections, particularly in low- and middle-income countries where traffic is multimodal, and infrastructure often lacks formal control. Demographic factors like age and gender significantly influence pedestrian vulnerability, yet real-time monitoring systems rarely capture this information. To address this gap, this study proposes a deep learning framework that classifies pedestrian age group and gender from far-view intersection footage using convolutional neural networks (CNNs), without relying on facial recognition or high-resolution imagery. The classification is structured as a unified six-class problem, distinguishing adult, teenager, and child pedestrians for both males and females, based on full-body visual cues. Video data was collected from three high-risk intersections in Dhaka, Bangladesh. Two CNN architectures were implemented: ResNet50, a deep convolutional neural network pretrained on ImageNet, and a custom lightweight CNN optimized for computational efficiency. Eight model variants explored combinations of pooling strategies and optimizers. ResNet50 with Max Pooling and SGD achieved the highest accuracy (86.19%), while the custom CNN performed comparably (84.15%) with fewer parameters and faster training. The model's efficient design enables real-time inference on standard surveillance feeds. For practitioners, this system provides a scalable, cost-effective tool to monitor pedestrian demographics at intersections using existing camera infrastructure. Its outputs can shape intersection design, optimize signal timing, and enable targeted safety interventions for vulnerable groups such as children or the elderly. By offering demographic insights often missing in conventional traffic data, the framework supports more inclusive, data-driven planning in mixed-traffic environments.	Accep... Accepted for poster presentation at the 105th Annual Meeting of the Transportation Research Board	None
LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations	2025-11-27	Show Video-based AI systems are increasingly adopted in safety-critical domains such as autonomous driving and healthcare. However, interpreting their decisions remains challenging due to the inherent spatiotemporal complexity of video data and the opacity of deep learning models. Existing explanation techniques often suffer from limited temporal coherence and a lack of actionable causal insights. Current counterfactual explanation methods typically do not incorporate guidance from the target model, reducing semantic fidelity and practical utility. We introduce Latent Diffusion for Video Counterfactual Explanations (LD-ViCE), a novel framework designed to explain the behavior of video-based AI models. Compared to previous approaches, LD-ViCE reduces the computational costs of generating explanations by operating in latent space using a state-of-the-art diffusion model, while producing realistic and interpretable counterfactuals through an additional refinement step. Experiments on three diverse video datasets - EchoNet-Dynamic (cardiac ultrasound), FERV39k (facial expression), and Something-Something V2 (action recognition) with multiple target models covering both classification and regression tasks, demonstrate that LD-ViCE generalizes well and achieves state-of-the-art performance. On the EchoNet-Dynamic dataset, LD-ViCE achieves significantly higher regression accuracy than prior methods and exhibits high temporal consistency, while the refinement stage further improves perceptual quality. Qualitative analyses confirm that LD-ViCE produces semantically meaningful and temporally coherent explanations, providing actionable insights into model behavior. LD-ViCE advances the trustworthiness and interpretability of video-based AI systems through visually coherent counterfactual explanations.	Under... Under Review CVPR 2026 (44 Pages)	None
Seeing without Pixels: Perception from Camera Trajectories	2025-11-26	Show Can one perceive a video's content without seeing its pixels, just from the camera trajectory-the path it carves through space? This paper is the first to systematically investigate this seemingly implausible question. Towards this end, we propose a contrastive learning framework to train CamFormer, a dedicated encoder that projects camera pose trajectories into a joint embedding space, aligning them with natural language. We find that, contrary to its apparent simplicity, the camera trajectory is a remarkably informative signal to uncover video content. In other words, "how you move" can indeed reveal "what you are doing" (egocentric) or "observing" (exocentric). We demonstrate the versatility of our learned CamFormer embeddings on a diverse suite of downstream tasks, ranging from cross-modal alignment to classification and temporal analysis. Importantly, our representations are robust across diverse camera pose estimation methods, including both high-fidelity multi-sensored and standard RGB-only estimators. Our findings establish camera trajectory as a lightweight, robust, and versatile modality for perceiving video content.	Proje... Project website: https://sites.google.com/view/seeing-without-pixels	None
AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs	2025-11-26	Show The threat of Audio-Video (AV) forgery is rapidly evolving beyond human-centric deepfakes to include more diverse manipulations across complex natural scenes. However, existing benchmarks are still confined to DeepFake-based forgeries and single-granularity annotations, thus failing to capture the diversity and complexity of real-world forgery scenarios. To address this, we introduce AVFakeBench, the first comprehensive audio-video forgery detection benchmark that spans rich forgery semantics across both human subject and general subject. AVFakeBench comprises 12K carefully curated audio-video questions, covering seven forgery types and four levels of annotations. To ensure high-quality and diverse forgeries, we propose a multi-stage hybrid forgery framework that integrates proprietary models for task planning with expert generative models for precise manipulation. The benchmark establishes a multi-task evaluation framework covering binary judgment, forgery types classification, forgery detail selection, and explanatory reasoning. We evaluate 11 Audio-Video Large Language Models (AV-LMMs) and 2 prevalent detection methods on AVFakeBench, demonstrating the potential of AV-LMMs as emerging forgery detectors while revealing their notable weaknesses in fine-grained perception and reasoning.		None
Dance Style Classification using Laban-Inspired and Frequency-Domain Motion Features	2025-11-25	Show Dance is an essential component of human culture and serves as a tool for conveying emotions and telling stories. Identifying and distinguishing dance genres based on motion data is a complex problem in human activity recognition, as many styles share similar poses, gestures, and temporal motion patterns. This work presents a lightweight framework for classifying dance styles that determines motion characteristics based on pose estimates extracted from videos. We propose temporal-spatial descriptors inspired by Laban Movement Analysis. These features capture local joint dynamics such as velocity, acceleration, and angular movement of the upper body, enabling a structured representation of spatial coordination. To further encode rhythmic and periodic aspects of movement, we integrate Fast Fourier Transform features that characterize movement patterns in the frequency domain. The proposed approach achieves robust classification of different dance styles with low computational effort, as complex model architectures are not required, and shows that interpretable motion representations can effectively capture stylistic nuances.		None
Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations	2025-11-25	Show Counterfactual explanations (CFEs) are minimal and semantically meaningful modifications of the input of a model that alter the model predictions. They highlight the decisive features the model relies on, providing contrastive interpretations for classifiers. State-of-the-art visual counterfactual explanation methods are designed to explain image classifiers. The generation of CFEs for video classifiers remains largely underexplored. For the counterfactual videos to be useful, they have to be physically plausible, temporally coherent, and exhibit smooth motion trajectories. Existing CFE image-based methods, designed to explain image classifiers, lack the capacity to generate temporally coherent, smooth and physically plausible video CFEs. To address this, we propose Back To The Feature (BTTF), an optimization framework that generates video CFEs. Our method introduces two novel features, 1) an optimization scheme to retrieve the initial latent noise conditioned by the first frame of the input video, 2) a two-stage optimization strategy to enable the search for counterfactual videos in the vicinity of the input video. Both optimization processes are guided solely by the target classifier, ensuring the explanation is faithful. To accelerate convergence, we also introduce a progressive optimization strategy that incrementally increases the number of denoising steps. Extensive experiments on video datasets such as Shape-Moving (motion classification), MEAD (emotion classification), and NTU RGB+D (action classification) show that our BTTF effectively generates valid, visually similar and realistic counterfactual videos that provide concrete insights into the classifier's decision-making mechanism.		None
MHB: Multimodal Handshape-aware Boundary Detection for Continuous Sign Language Recognition	2025-11-25	Show This paper presents a multimodal approach for continuous sign recognition that first uses machine learning to detect the start and end frames of signs in videos of American Sign Language (ASL) sentences, and then recognizes the segmented signs. For improved robustness, we use 3D skeletal features extracted from sign language videos to capture the convergence of sign properties and their dynamics, which tend to cluster at sign boundaries. Another focus of this work is the incorporation of information from 3D handshape for boundary detection. To detect handshapes normally expected at the beginning and end of signs, we pretrain a handshape classifier for 87 linguistically defined canonical handshape categories using a dataset that we created by integrating and normalizing several existing datasets. A multimodal fusion module is then used to unify the pretrained sign video segmentation framework and the handshape classification models. Finally, the estimated boundaries are used for sign recognition, where the recognition model is trained on a large database containing both citation-form isolated signs and signs pre-segmented (based on manual annotations) from continuous signing, as such signs often differ in certain respects. We evaluate our method on the ASLLRP corpus and demonstrate significant improvements over previous work.		None
TouchFormer: A Robust Transformer-based Framework for Multimodal Material Perception	2025-11-24	Show Traditional vision-based material perception methods often experience substantial performance degradation under visually impaired conditions, thereby motivating the shift toward non-visual multimodal material perception. Despite this, existing approaches frequently perform naive fusion of multimodal inputs, overlooking key challenges such as modality-specific noise, missing modalities common in real-world scenarios, and the dynamically varying importance of each modality depending on the task. These limitations lead to suboptimal performance across several benchmark tasks. In this paper, we propose a robust multimodal fusion framework, TouchFormer. Specifically, we employ a Modality-Adaptive Gating (MAG) mechanism and intra- and inter-modality attention mechanisms to adaptively integrate cross-modal features, enhancing model robustness. Additionally, we introduce a Cross-Instance Embedding Regularization(CER) strategy, which significantly improves classification accuracy in fine-grained subcategory material recognition tasks. Experimental results demonstrate that, compared to existing non-visual methods, the proposed TouchFormer framework achieves classification accuracy improvements of 2.48% and 6.83% on SSMC and USMC tasks, respectively. Furthermore, real-world robotic experiments validate TouchFormer's effectiveness in enabling robots to better perceive and interpret their environment, paving the way for its deployment in safety-critical applications such as emergency response and industrial automation. The code and datasets will be open-source, and the videos are available in the supplementary materials.	9 pag... 9 pages, 7 figures, Accepted by AAAI 2026	None
CataractCompDetect: Intraoperative Complication Detection in Cataract Surgery	2025-11-24	Show Cataract surgery is one of the most commonly performed surgeries worldwide, yet intraoperative complications such as iris prolapse, posterior capsule rupture (PCR), and vitreous loss remain major causes of adverse outcomes. Automated detection of such events could enable early warning systems and objective training feedback. In this work, we propose CataractCompDetect, a complication detection framework that combines phase-aware localization, SAM 2-based tracking, complication-specific risk scoring, and vision-language reasoning for final classification. To validate CataractCompDetect, we curate CataComp, the first cataract surgery video dataset annotated for intraoperative complications, comprising 53 surgeries, including 23 with clinical complications. On CataComp, CataractCompDetect achieves an average F1 score of 70.63%, with per-complication performance of 81.8% (Iris Prolapse), 60.87% (PCR), and 69.23% (Vitreous Loss). These results highlight the value of combining structured surgical priors with vision-language reasoning for recognizing rare but high-impact intraoperative events. Our dataset and code will be publicly released upon acceptance.		None
When Top-ranked Recommendations Fail: Modeling Multi-Granular Negative Feedback for Explainable and Robust Video Recommendation	2025-11-24	Show Existing video recommendation systems, relying mainly on ID-based embedding mapping and collaborative filtering, often fail to capture in-depth video content semantics. Moreover, most struggle to address biased user behaviors (e.g., accidental clicks, fast skips), leading to inaccurate interest modeling and frequent negative feedback in top recommendations with unclear causes. To tackle this issue, we collect real-world user video-watching sequences, annotate the reasons for users' dislikes, and construct a benchmark dataset for personalized explanations. We then introduce the Agentic Explainable Negative Feedback (ENF) framework, which integrates three core components: (1) the Profile Agent, extracting behavioral cues from users' historical data to derive psychological and personality profiles; (2) the Video Agent, performing comprehensive multimodal video analysis; and (3) the Reason Agent, synthesizing information from the other two agents to predict user engagement and generate explanations. Additionally, we propose the S-GRPO algorithm, enabling the model to progressively address complex tasks during reinforcement fine-tuning. Experimental results on the collected dataset show that our method significantly outperforms state-of-the-art baselines in negative feedback prediction and reason explanation. Notably, it achieves an 8.6% improvement over GPT-4o in reason classification. Deployment on the business platform further validates its benefits: increasing average user watch time by 6.2%, reducing the fast-skip rate by 9.4%, and significantly enhancing user satisfaction.	Accep... Accepted in AAAI 2026	None
MTikGuard System: A Transformer-Based Multimodal System for Child-Safe Content Moderation on TikTok	2025-11-22	Show With the rapid rise of short-form videos, TikTok has become one of the most influential platforms among children and teenagers, but also a source of harmful content that can affect their perception and behavior. Such content, often subtle or deceptive, challenges traditional moderation methods due to the massive volume and real-time nature of uploads. This paper presents MTikGuard, a real-time multimodal harmful content detection system for TikTok, with three key contributions: (1) an extended TikHarm dataset expanded to 4,723 labeled videos by adding diverse real-world samples, (2) a multimodal classification framework integrating visual, audio, and textual features to achieve state-of-the-art performance with 89.37% accuracy and 89.45% F1-score, and (3) a scalable streaming architecture built on Apache Kafka and Apache Spark for real-time deployment. The results demonstrate the effectiveness of combining dataset expansion, advanced multimodal fusion, and robust deployment for practical large-scale social media content moderation. The dataset is available at https://github.com/ntdat-8324/MTikGuard-System.git.	Accepted at PACLIC39	Code Link
Three-Class Emotion Classification for Audiovisual Scenes Based on Ensemble Learning Scheme	2025-11-22	Show Emotion recognition plays a pivotal role in enhancing human-computer interaction, particularly in movie recommendation systems where understanding emotional content is essential. While multimodal approaches combining audio and video have demonstrated effectiveness, their reliance on high-performance graphical computing limits deployment on resource-constrained devices such as personal computers or home audiovisual systems. To address this limitation, this study proposes a novel audio-only ensemble learning framework capable of classifying movie scenes into three emotional categories: Good, Neutral, and Bad. The model integrates ten support vector machines and six neural networks within a stacking ensemble architecture to enhance classification performance. A tailored data preprocessing pipeline, including feature extraction, outlier handling, and feature engineering, is designed to optimize emotional information from audio inputs. Experiments on a simulated dataset achieve 67% accuracy, while a real-world dataset collected from 15 diverse films yields an impressive 86% accuracy. These results underscore the potential of audio-based, lightweight emotion recognition methods for broader consumer-level applications, offering both computational efficiency and robust classification capabilities.		None
Point-Supervised Facial Expression Spotting with Gaussian-Based Instance-Adaptive Intensity Modeling	2025-11-21	Show Automatic facial expression spotting, which aims to identify facial expression instances in untrimmed videos, is crucial for facial expression analysis. Existing methods primarily focus on fully-supervised learning and rely on costly, time-consuming temporal boundary annotations. In this paper, we investigate point-supervised facial expression spotting (P-FES), where only a single timestamp annotation per instance is required for training. We propose a unique two-branch framework for P-FES. First, to mitigate the limitation of hard pseudo-labeling, which often confuses neutral and expression frames with various intensities, we propose a Gaussian-based instance-adaptive intensity modeling (GIM) module to model instance-level expression intensity distribution for soft pseudo-labeling. By detecting the pseudo-apex frame around each point label, estimating the duration, and constructing an instance-level Gaussian distribution, GIM assigns soft pseudo-labels to expression frames for more reliable intensity supervision. The GIM module is incorporated into our framework to optimize the class-agnostic expression intensity branch. Second, we design a class-aware apex classification branch that distinguishes macro- and micro-expressions solely based on their pseudo-apex frames. During inference, the two branches work independently: the class-agnostic expression intensity branch generates expression proposals, while the class-aware apex-classification branch is responsible for macro- and micro-expression classification.Furthermore, we introduce an intensity-aware contrastive loss to enhance discriminative feature learning and suppress neutral noise by contrasting neutral frames with expression frames with various intensities. Extensive experiments on the SAMM-LV, CAS(ME)$^2$, and CAS(ME)$^3$ datasets demonstrate the effectiveness of our proposed framework.		None
BoxingVI: A Multi-Modal Benchmark for Boxing Action Recognition and Localization	2025-11-20	Show Accurate analysis of combat sports using computer vision has gained traction in recent years, yet the development of robust datasets remains a major bottleneck due to the dynamic, unstructured nature of actions and variations in recording environments. In this work, we present a comprehensive, well-annotated video dataset tailored for punch detection and classification in boxing. The dataset comprises 6,915 high-quality punch clips categorized into six distinct punch types, extracted from 20 publicly available YouTube sparring sessions and involving 18 different athletes. Each clip is manually segmented and labeled to ensure precise temporal boundaries and class consistency, capturing a wide range of motion styles, camera angles, and athlete physiques. This dataset is specifically curated to support research in real-time vision-based action recognition, especially in low-resource and unconstrained environments. By providing a rich benchmark with diverse punch examples, this contribution aims to accelerate progress in movement analysis, automated coaching, and performance assessment within boxing and related domains.		None
From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos	2025-11-20	Show Composed Video Retrieval (CoVR) retrieves a target video given a query video and a modification text describing the intended change. Existing CoVR benchmarks emphasize appearance shifts or coarse event changes and therefore do not test the ability to capture subtle, fast-paced temporal differences. We introduce TF-CoVR, the first large-scale benchmark dedicated to temporally fine-grained CoVR. TF-CoVR focuses on gymnastics and diving, and provides 180K triplets drawn from FineGym and FineDiving datasets. Previous CoVR benchmarks, focusing on temporal aspect, link each query to a single target segment taken from the same video, limiting practical usefulness. In TF-CoVR, we instead construct each pair by prompting an LLM with the label differences between clips drawn from different videos; every pair is thus associated with multiple valid target videos (3.9 on average), reflecting real-world tasks such as sports-highlight generation. To model these temporal dynamics, we propose TF-CoVR-Base, a concise two-stage training framework: (i) pre-train a video encoder on fine-grained action classification to obtain temporally discriminative embeddings; (ii) align the composed query with candidate videos using contrastive learning. We conduct the first comprehensive study of image, video, and general multimodal embedding (GME) models on temporally fine-grained composed retrieval in both zero-shot and fine-tuning regimes. On TF-CoVR, TF-CoVR-Base improves zero-shot mAP@50 from 5.92 (LanguageBind) to 7.51, and after fine-tuning raises the state-of-the-art from 19.83 to 27.22.		None
Degradation-Aware Hierarchical Termination for Blind Quality Enhancement of Compressed Video	2025-11-20	Show Existing studies on Quality Enhancement for Compressed Video (QECV) predominantly rely on known Quantization Parameters (QPs), employing distinct enhancement models per QP setting, termed non-blind methods. However, in real-world scenarios involving transcoding or transmission, QPs may be partially or entirely unknown, limiting the applicability of such approaches and motivating the development of blind QECV techniques. Current blind methods generate degradation vectors via classification models with cross-entropy loss, using them as channel attention to guide artifact removal. However, these vectors capture only global degradation information and lack spatial details, hindering adaptation to varying artifact patterns at different spatial positions. To address these limitations, we propose a pretrained Degradation Representation Learning (DRL) module that decouples and extracts high-dimensional, multiscale degradation representations from video content to guide the artifact removal. Additionally, both blind and non-blind methods typically employ uniform architectures across QPs, hence, overlooking the varying computational demands inherent to different compression levels. We thus introduce a hierarchical termination mechanism that dynamically adjusts the number of artifact reduction stages based on the compression level. Experimental results demonstrate that the proposed approach significantly enhances performance, achieving a PSNR improvement of 110% (from 0.31 dB to 0.65 dB) over a competing state-of-the-art blind method at QP = 22. Furthermore, the proposed hierarchical termination mechanism reduces the average inference time at QP = 22 by half compared to QP = 42.		None
Click2Graph: Interactive Panoptic Video Scene Graphs from a Single Click	2025-11-20	Show State-of-the-art Video Scene Graph Generation (VSGG) systems provide structured visual understanding but operate as closed, feed-forward pipelines with no ability to incorporate human guidance. In contrast, promptable segmentation models such as SAM2 enable precise user interaction but lack semantic or relational reasoning. We introduce Click2Graph, the first interactive framework for Panoptic Video Scene Graph Generation (PVSG) that unifies visual prompting with spatial, temporal, and semantic understanding. From a single user cue, such as a click or bounding box, Click2Graph segments and tracks the subject across time, autonomously discovers interacting objects, and predicts triplets to form a temporally consistent scene graph. Our framework introduces two key components: a Dynamic Interaction Discovery Module that generates subject-conditioned object prompts, and a Semantic Classification Head that performs joint entity and predicate reasoning. Experiments on the OpenPVSG benchmark demonstrate that Click2Graph establishes a strong foundation for user-guided PVSG, showing how human prompting can be combined with panoptic grounding and relational inference to enable controllable and interpretable video scene understanding.		None
RB-FT: Rationale-Bootstrapped Fine-Tuning for Video Classification	2025-11-19	Show Vision Language Models (VLMs) are becoming increasingly integral to multimedia understanding; however, they often struggle with domain-specific video classification tasks, particularly in cases with limited data. This stems from a critical \textit{rationale gap}, where sparse domain data is insufficient to bridge the semantic distance between complex spatio-temporal content and abstract classification labels. We propose a two-stage self-improvement paradigm to bridge this gap without new annotations. First, we prompt the VLMs to generate detailed textual rationales for each video, compelling them to articulate the domain-specific logic. The VLM is then fine-tuned on these self-generated rationales, utilizing this intermediate supervision to align its representations with the nuances of the target domain. Second, conventional supervised fine-tuning (SFT) is performed on the task labels, achieving markedly higher effectiveness as a result of the model's pre-acquired domain reasoning. Extensive experiments on diverse datasets demonstrate that our method significantly outperforms direct SFT, validating self-generated rationale as an effective, annotation-efficient paradigm for adapting VLMs to domain-specific video analysis.	11 pages, 2 figures	None
MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features	2025-11-19	Show Eye tracking data quantifies the attentional bias towards negative stimuli that is frequently observed in depressed groups. Audio and video data capture the affective flattening and psychomotor retardation characteristic of depression. Statistical validation confirmed their significant discriminative power in distinguishing depressed from non depressed groups. We address a critical limitation of existing graph-based models that focus on low-frequency information and propose a Multi-Frequency Graph Convolutional Network (MF-GCN). This framework consists of a novel Multi-Frequency Filter Bank Module (MFFBM), which can leverage both low and high frequency signals. Extensive evaluation against traditional machine learning algorithms and deep learning frameworks demonstrates that MF-GCN consistently outperforms baselines. In binary (depressed and non depressed) classification, the model achieved a sensitivity of 0.96 and F2 score of 0.94. For the 3 class (no depression, mild to moderate depression and severe depression) classification task, the proposed method achieved a sensitivity of 0.79 and specificity of 0.87 and siginificantly suprassed other models. To validate generalizability, the model was also evaluated on the Chinese Multimodal Depression Corpus (CMDC) dataset and achieved a sensitivity of 0.95 and F2 score of 0.96. These results confirm that our trimodal, multi frequency framework effectively captures cross modal interaction for accurate depression detection.		None
Deep Learning for Accurate Vision-based Catch Composition in Tropical Tuna Purse Seiners	2025-11-19	Show Purse seiners play a crucial role in tuna fishing, as approximately 69% of the world's tropical tuna is caught using this gear. All tuna Regional Fisheries Management Organizations have established minimum standards to use electronic monitoring (EM) in fisheries in addition to traditional observers. The EM systems produce a massive amount of video data that human analysts must process. Integrating artificial intelligence (AI) into their workflow can decrease that workload and improve the accuracy of the reports. However, species identification still poses significant challenges for AI, as achieving balanced performance across all species requires appropriate training data. Here, we quantify the difficulty experts face to distinguish bigeye tuna (BET, Thunnus Obesus) from yellowfin tuna (YFT, Thunnus Albacares) using images captured by EM systems. We found inter-expert agreements of 42.9% $\pm$ 35.6% for BET and 57.1% $\pm$ 35.6% for YFT. We then present a multi-stage pipeline to estimate the species composition of the catches using a reliable ground-truth dataset based on identifications made by observers on board. Three segmentation approaches are compared: Mask R-CNN, a combination of DINOv2 with SAM2, and a integration of YOLOv9 with SAM2. We found that the latest performs the best, with a validation mean average precision of 0.66 $\pm$ 0.03 and a recall of 0.88 $\pm$ 0.03. Segmented individuals are tracked using ByteTrack. For classification, we evaluate a standard multiclass classification model and a hierarchical approach, finding a superior generalization by the hierarchical. All our models were cross-validated during training and tested on fishing operations with fully known catch composition. Combining YOLOv9-SAM2 with the hierarchical classification produced the best estimations, with 84.8% of the individuals being segmented and classified with a mean average error of 4.5%.	23 pages, 5 figures	None
A Multimodal Transformer Approach for UAV Detection and Aerial Object Recognition Using Radar, Audio, and Video Data	2025-11-19	Show Unmanned aerial vehicle (UAV) detection and aerial object recognition are critical for modern surveillance and security, prompting a need for robust systems that overcome limitations of single-modality approaches. This research addresses these challenges by designing and rigorously evaluating a novel multimodal Transformer model that integrates diverse data streams: radar, visual band video (RGB), infrared (IR) video, and audio. The architecture effectively fuses distinct features from each modality, leveraging the Transformer's self-attention mechanisms to learn comprehensive, complementary, and highly discriminative representations for classification. The model demonstrated exceptional performance on an independent test set, achieving macro-averaged metrics of 0.9812 accuracy, 0.9873 recall, 0.9787 precision, 0.9826 F1-score, and 0.9954 specificity. Notably, it exhibited particularly high precision and recall in distinguishing drones from other aerial objects. Furthermore, computational analysis confirmed its efficiency, with 1.09 GFLOPs, 1.22 million parameters, and an inference speed of 41.11 FPS, highlighting its suitability for real-time applications. This study presents a significant advancement in aerial object classification, validating the efficacy of multimodal data fusion via a Transformer architecture for achieving state-of-the-art performance, thereby offering a highly accurate and resilient solution for UAV detection and monitoring in complex airspace.	23 pages, 7 figures	None
Vision Large Language Models Are Good Noise Handlers in Engagement Analysis	2025-11-18	Show Engagement recognition in video datasets, unlike traditional image classification tasks, is particularly challenged by subjective labels and noise limiting model performance. To overcome the challenges of subjective and noisy engagement labels, we propose a framework leveraging Vision Large Language Models (VLMs) to refine annotations and guide the training process. Our framework uses a questionnaire to extract behavioral cues and split data into high- and low-reliability subsets. We also introduce a training strategy combining curriculum learning with soft label refinement, gradually incorporating ambiguous samples while adjusting supervision to reflect uncertainty. We demonstrate that classical computer vision models trained on refined high-reliability subsets and enhanced with our curriculum strategy show improvements, highlighting benefits of addressing label subjectivity with VLMs. This method surpasses prior state of the art across engagement benchmarks such as EngageNet (three of six feature settings, maximum improvement of +1.21%), and DREAMS / PAFE with F1 gains of +0.22 / +0.06.		None
Logos as a Well-Tempered Pre-train for Sign Language Recognition	2025-11-18	Show This paper examines two aspects of the isolated sign language recognition (ISLR) task. First, although a certain number of datasets is available, the data for individual sign languages is limited. It poses the challenge of cross-language ISLR model training, including transfer learning. Second, similar signs can have different semantic meanings. It leads to ambiguity in dataset labeling and raises the question of the best policy for annotating such signs. To address these issues, this study presents Logos, a novel Russian Sign Language (RSL) dataset, the most extensive available ISLR dataset by the number of signers, one of the most extensive datasets in size and vocabulary, and the largest RSL dataset. It is shown that a model, pre-trained on the Logos dataset can be used as a universal encoder for other language SLR tasks, including few-shot learning. We explore cross-language transfer learning approaches and find that joint training using multiple classification heads benefits accuracy for the target low-resource datasets the most. The key feature of the Logos dataset is explicitly annotated visually similar sign groups. We show that explicitly labeling visually similar signs improves trained model quality as a visual encoder for downstream tasks. Based on the proposed contributions, we outperform current state-of-the-art results for the WLASL dataset and get competitive results for the AUTSL dataset, with a single stream model processing solely RGB video. The source code, dataset, and pre-trained models are publicly available.		None
Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines	2025-11-18	Show Newborns perceive the world with low-acuity, color-degraded, and temporally continuous vision, which gradually sharpens as infants develop. To explore the ecological advantages of such staged "visual diets", we train self-supervised learning (SSL) models on object-centric videos under constraints that simulate infant vision: grayscale-to-color (C), blur-to-sharp (A), and preserved temporal continuity (T)-collectively termed CATDiet. For evaluation, we establish a comprehensive benchmark across ten datasets, covering clean and corrupted image recognition, texture-shape cue conflict tests, silhouette recognition, depth-order classification, and the visual cliff paradigm. All CATDiet variants demonstrate enhanced robustness in object recognition, despite being trained solely on object-centric videos. Remarkably, models also exhibit biologically aligned developmental patterns, including neural plasticity changes mirroring synaptic density in macaque V1 and behaviors resembling infants' visual cliff responses. Building on these insights, CombDiet initializes SSL with CATDiet before standard training while preserving temporal continuity. Trained on object-centric or head-mounted infant videos, CombDiet outperforms standard SSL on both in-domain and out-of-domain object recognition and depth perception. Together, these results suggest that the developmental progression of early infant visual experience offers a powerful reverse-engineering framework for understanding the emergence of robust visual intelligence in machines. All code, data, and models will be publicly released.		None
EBind: a practical approach to space binding	2025-11-18	Show We simplify space binding by focusing on two core components, a single encoder per modality and high-quality data; enabling training state-of-the-art models on a single GPU in a few hours as opposed to multiple days. We present EBind, an Easy, data-centric, and parameter-efficient method to Bind the embedding spaces of multiple contrastive models. We demonstrate that a simple 1.8B-parameter image-text-video-audio-3D model can outperform models 4 to 17x the size. The key to achieving this is a carefully curated dataset of three complementary data sources: i) 6.7M fully-automated multimodal quintuples sourced via SOTA retrieval models, ii) 1M diverse, semi-automated triples annotated by humans as negative, partial, or positive matches, and iii) 3.4M pre-existing captioned data items. We use 13 different evaluations to demonstrate the value of each data source. Due to limitations with existing benchmarks, we further introduce the first high-quality, consensus-annotated zero-shot classification benchmark between audio and PCs. In contrast to related work, we will open-source our code, model weights, and datasets.		None
Temporal Realism Evaluation of Generated Videos Using Compressed-Domain Motion Vectors	2025-11-17	Show Temporal realism remains a central weakness of current generative video models, as most evaluation metrics prioritize spatial appearance and offer limited sensitivity to motion. We introduce a scalable, model-agnostic framework that assesses temporal behavior using motion vectors (MVs) extracted directly from compressed video streams. Codec-generated MVs from standards such as H.264 and HEVC provide lightweight, resolution-consistent descriptors of motion dynamics. We quantify realism by computing Kullback-Leibler, Jensen-Shannon, and Wasserstein divergences between MV statistics of real and generated videos. Experiments on the GenVidBench dataset containing videos from eight state-of-the-art generators reveal systematic discrepancies from real motion: entropy-based divergences rank Pika and SVD as closest to real videos, MV-sum statistics favor VC2 and Text2Video-Zero, and CogVideo shows the largest deviations across both measures. Visualizations of MV fields and class-conditional motion heatmaps further reveal center bias, sparse and piecewise constant flows, and grid-like artifacts that frame-level metrics do not capture. Beyond evaluation, we investigate MV-RGB fusion through channel concatenation, cross-attention, joint embedding, and a motion-aware fusion module. Incorporating MVs improves downstream classification across ResNet, I3D, and TSN backbones, with ResNet-18 and ResNet-34 reaching up to 97.4% accuracy and I3D achieving 99.0% accuracy on real-versus-generated discrimination. These findings demonstrate that compressed-domain MVs provide an effective temporal signal for diagnosing motion defects in generative videos and for strengthening temporal reasoning in discriminative models. The implementation is available at: https://github.com/KurbanIntelligenceLab/Motion-Vector-Learning		Code Link
Temporal Object-Aware Vision Transformer for Few-Shot Video Object Detection	2025-11-16	Show Few-shot Video Object Detection (FSVOD) addresses the challenge of detecting novel objects in videos with limited labeled examples, overcoming the constraints of traditional detection methods that require extensive training data. This task presents key challenges, including maintaining temporal consistency across frames affected by occlusion and appearance variations, and achieving novel object generalization without relying on complex region proposals, which are often computationally expensive and require task-specific training. Our novel object-aware temporal modeling approach addresses these challenges by incorporating a filtering mechanism that selectively propagates high-confidence object features across frames. This enables efficient feature progression, reduces noise accumulation, and enhances detection accuracy in a few-shot setting. By utilizing few-shot trained detection and classification heads with focused feature propagation, we achieve robust temporal consistency without depending on explicit object tube proposals. Our approach achieves performance gains, with AP improvements of 3.7% (FSVOD-500), 5.3% (FSYTV-40), 4.3% (VidOR), and 4.5 (VidVRD) in the 5-shot setting. Further results demonstrate improvements in 1-shot, 3-shot, and 10-shot configurations. We make the code public at: https://github.com/yogesh-iitj/fs-video-vit	Accep... Accepted at AAAI 2026 Main Track	Code Link
Learning Time in Static Classifiers	2025-11-15	Show Real-world visual data rarely presents as isolated, static instances. Instead, it often evolves gradually over time through variations in pose, lighting, object state, or scene context. However, conventional classifiers are typically trained under the assumption of temporal independence, limiting their ability to capture such dynamics. We propose a simple yet effective framework that equips standard feedforward classifiers with temporal reasoning, all without modifying model architectures or introducing recurrent modules. At the heart of our approach is a novel Support-Exemplar-Query (SEQ) learning paradigm, which structures training data into temporally coherent trajectories. These trajectories enable the model to learn class-specific temporal prototypes and align prediction sequences via a differentiable soft-DTW loss. A multi-term objective further promotes semantic consistency and temporal smoothness. By interpreting input sequences as evolving feature trajectories, our method introduces a strong temporal inductive bias through loss design alone. This proves highly effective in both static and temporal tasks: it enhances performance on fine-grained and ultra-fine-grained image classification, and delivers precise, temporally consistent predictions in video anomaly detection. Despite its simplicity, our approach bridges static and temporal learning in a modular and data-efficient manner, requiring only a simple classifier on top of pre-extracted features.	Accep... Accepted at the Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026)	None
OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs	2025-11-15	Show Existing sparse attention methods primarily target inference-time acceleration by selecting critical tokens under predefined sparsity patterns. However, they often fail to bridge the training-inference gap and lack the capacity for fine-grained token selection across multiple dimensions such as queries, key-values (KV), and heads, leading to suboptimal performance and limited acceleration gains. In this paper, we introduce OmniSparse, a training-aware fine-grained sparse attention framework for long-video MLLMs, which operates in both training and inference with dynamic token budget allocation. Specifically, OmniSparse contains three adaptive and complementary mechanisms: (1) query selection via lazy-active classification, retaining active queries that capture broad semantic similarity while discarding most lazy ones that focus on limited local context and exhibit high functional redundancy; (2) KV selection with head-level dynamic budget allocation, where a shared budget is determined based on the flattest head and applied uniformly across all heads to ensure attention recall; and (3) KV cache slimming to reduce head-level redundancy by selectively fetching visual KV cache according to the head-level decoding query pattern. Experimental results show that OmniSparse matches the performance of full attention while achieving up to 2.7x speedup during prefill and 2.4x memory reduction during decoding.	Accepted by AAAI2026	None
SITE: towards Spatial Intelligence Thorough Evaluation	2025-11-15	Show Spatial intelligence (SI) represents a cognitive ability encompassing the visualization, manipulation, and reasoning about spatial relationships, underpinning disciplines from neuroscience to robotics. We introduce SITE, a benchmark dataset towards SI Thorough Evaluation in a standardized format of multi-choice visual question-answering, designed to assess large vision-language models' spatial intelligence across diverse visual modalities (single-image, multi-image, and video) and SI factors (figural to environmental scales, spatial visualization and orientation, intrinsic and extrinsic, static and dynamic). Our approach to curating the benchmark combines a bottom-up survey about 31 existing datasets and a top-down strategy drawing upon three classification systems in cognitive science, which prompt us to design two novel types of tasks about view-taking and dynamic scenes. Extensive experiments reveal that leading models fall behind human experts especially in spatial orientation, a fundamental SI factor. Moreover, we demonstrate a positive correlation between a model's spatial reasoning proficiency and its performance on an embodied AI task.	Accep... Accepted to ICCV 2025	None
End to End AI System for Surgical Gesture Sequence Recognition and Clinical Outcome Prediction	2025-11-14	Show Fine-grained analysis of intraoperative behavior and its impact on patient outcomes remain a longstanding challenge. We present Frame-to-Outcome (F2O), an end-to-end system that translates tissue dissection videos into gesture sequences and uncovers patterns associated with postoperative outcomes. Leveraging transformer-based spatial and temporal modeling and frame-wise classification, F2O robustly detects consecutive short (2 seconds) gestures in the nerve-sparing step of robot-assisted radical prostatectomy (AUC: 0.80 frame-level; 0.81 video-level). F2O-derived features (gesture frequency, duration, and transitions) predicted postoperative outcomes with accuracy comparable to human annotations (0.79 vs. 0.75; overlapping 95% CI). Across 25 shared features, effect size directions were concordant with small differences ( 0.07), and strong correlation (r = 0.96, p < 1e-14). F2O also captured key patterns linked to erectile function recovery, including prolonged tissue peeling and reduced energy use. By enabling automatic interpretable assessment, F2O establishes a foundation for data-driven surgical feedback and prospective clinical decision support.		None
A Space-Time Transformer for Precipitation Forecasting	2025-11-14	Show Meteorological agencies around the world rely on real-time flood guidance to issue live-saving advisories and warnings. For decades traditional numerical weather prediction (NWP) models have been state-of-the-art for precipitation forecasting. However, physically-parameterized models suffer from a few core limitations: first, solving PDEs to resolve atmospheric dynamics is computationally demanding, and second, these methods degrade in performance at nowcasting timescales (i.e., 0-4 hour lead-times). Motivated by these shortcomings, recent work proposes AI-weather prediction (AI-WP) alternatives that learn to emulate analysis data with neural networks. While these data-driven approaches have enjoyed enormous success across diverse spatial and temporal resolutions, applications of video-understanding architectures for weather forecasting remain underexplored. To address these gaps, we propose SaTformer: a video transformer built on full space-time attention that skillfully forecasts extreme precipitation from satellite radiances. Along with our novel architecture, we introduce techniques to tame long-tailed precipitation datasets. Namely, we reformulate precipitation regression into a classification problem, and employ a class-weighted loss to address label imbalances. Our model scored first place on the NeurIPS Weather4Cast 2025 Cumulative Rainfall challenge. Code and model weights are available: https://github.com/leharris3/satformer		Code Link
Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment	2025-11-13	Show Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances and classify categories. However, their objectives may tend to detect the most salient response segments, while neglecting to mine diverse normal patterns separated from anomalies, and are prone to category confusion due to similar appearance, leading to unsatisfactory fine-grained classification results. Therefore, we propose a novel Disentangled Semantic Alignment Network (DSANet) to explicitly separate abnormal and normal features from coarse-grained and fine-grained aspects, enhancing the distinguishability. Specifically, at the coarse-grained level, we introduce a self-guided normality modeling branch that reconstructs input video features under the guidance of learned normal prototypes, encouraging the model to exploit normality cues inherent in the video, thereby improving the temporal separation of normal patterns and anomalous events. At the fine-grained level, we present a decoupled contrastive semantic alignment mechanism, which first temporally decomposes each video into event-centric and background-centric components using frame-level anomaly scores and then applies visual-language contrastive learning to enhance class-discriminative representations. Comprehensive experiments on two standard benchmarks, namely XD-Violence and UCF-Crime, demonstrate that DSANet outperforms existing state-of-the-art methods.	Accep... Accepted to AAAI 2026. Code is available at https://github.com/lessiYin/DSANet	Code Link
SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition	2025-11-13	Show Large Language Models (LLMs) hold rich implicit knowledge and powerful transferability. In this paper, we explore the combination of LLMs with the human skeleton to perform action classification and description. However, when treating LLM as a recognizer, two questions arise: 1) How can LLMs understand skeleton? 2) How can LLMs distinguish among actions? To address these problems, we introduce a novel paradigm named learning Skeleton representation with visUal-motion knowledGe for Action Recognition (SUGAR). In our pipeline, we first utilize off-the-shelf large-scale video models as a knowledge base to generate visual, motion information related to actions. Then, we propose to supervise skeleton learning through this prior knowledge to yield discrete representations. Finally, we use the LLM with untouched pre-training weights to understand these representations and generate the desired action targets and descriptions. Notably, we present a Temporal Query Projection (TQP) module to continuously model the skeleton signals with long sequences. Experiments on several skeleton-based action classification benchmarks demonstrate the efficacy of our SUGAR. Moreover, experiments on zero-shot scenarios show that SUGAR is more versatile than linear-based methods.	Accep... Accepted by AAAI 2026 Main Track	None
evMLP: An Efficient Event-Driven MLP Architecture for Vision	2025-11-12	Show Deep neural networks have achieved remarkable results in computer vision tasks. In the early days, Convolutional Neural Networks (CNNs) were the mainstream architecture. In recent years, Vision Transformers (ViTs) have become increasingly popular. In addition, exploring applications of multi-layer perceptrons (MLPs) has provided new perspectives for research into vision model architectures. In this paper, we present evMLP accompanied by a simple event-driven local update mechanism. The proposed evMLP can independently process patches on images or feature maps via MLPs. We define changes between consecutive frames as ``events''. Under the event-driven local update mechanism, evMLP selectively processes patches where events occur. For sequential image data (e.g., video processing), this approach improves computational performance by avoiding redundant computations. Through ImageNet image classification experiments, evMLP attains accuracy competitive with state-of-the-art models. More significantly, experimental results on multiple video datasets demonstrate that evMLP reduces computational cost via its event-driven local update mechanism while maintaining output consistency with its non-event-driven baseline. The code and pre-trained models are available at https://github.com/i-evi/evMLP.		Code Link
Auto-US: An Ultrasound Video Diagnosis Agent Using Video Classification Framework and LLMs	2025-11-12	Show AI-assisted ultrasound video diagnosis presents new opportunities to enhance the efficiency and accuracy of medical imaging analysis. However, existing research remains limited in terms of dataset diversity, diagnostic performance, and clinical applicability. In this study, we propose \textbf{Auto-US}, an intelligent diagnosis agent that integrates ultrasound video data with clinical diagnostic text. To support this, we constructed \textbf{CUV Dataset} of 495 ultrasound videos spanning five categories and three organs, aggregated from multiple open-access sources. We developed \textbf{CTU-Net}, which achieves state-of-the-art performance in ultrasound video classification, reaching an accuracy of 86.73% Furthermore, by incorporating large language models, Auto-US is capable of generating clinically meaningful diagnostic suggestions. The final diagnostic scores for each case exceeded 3 out of 5 and were validated by professional clinicians. These results demonstrate the effectiveness and clinical potential of Auto-US in real-world ultrasound applications. Code and data are available at: https://github.com/Bean-Young/Auto-US.	Under Review	Code Link
Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance	2025-11-11	Show Short video platforms are evolving rapidly, making the identification of inappropriate content increasingly critical. Existing approaches typically train separate and small classification models for each type of issue, which requires extensive human-labeled data and lacks cross-issue generalization. We propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection. To address the distribution gap between short video content and the original pretraining data of MLLMs, as well as the complex issue definitions, we introduce three targeted pretraining tasks: (1) \textit{Caption}, to enhance the MLLM's perception of video details; (2) \textit{Visual Question Answering (VQA)}, to deepen the MLLM's understanding of issue definitions and annotation guidelines; (3) \textit{Chain-of-Thought (CoT)}, to enhance the MLLM's reasoning capability. Experimental results show that our pretraining approach significantly improves the MLLM's performance in both zero-shot and supervised fine-tuning (SFT) settings. In addition, our pretrained model demonstrates strong generalization capabilities to emergent, previously unseen issues.	Camer... Camera Ready for EMNLP 2025	None
"Whose Side Are You On?" Estimating Ideology of Political and News Content Using Large Language Models and Few-shot Demonstration Selection	2025-11-11	Show The rapid growth of social media platforms has led to concerns about radicalization, filter bubbles, and content bias. Existing approaches to classifying ideology are limited in that they require extensive human effort, the labeling of large datasets, and are not able to adapt to evolving ideological contexts. This paper explores the potential of Large Language Models (LLMs) for classifying the political ideology of online content through in-context learning (ICL). Our extensive experiments involving demonstration selection in label-balanced fashion, conducted on three datasets comprising news articles and YouTube videos, reveal that our approach significantly outperforms zero-shot and traditional supervised methods. Additionally, we evaluate the influence of metadata (e.g., content source and descriptions) on ideological classification and discuss its implications. Finally, we show how providing the source for political and non-political content influences the LLM's classification.		None
HCFSLN: Adaptive Hyperbolic Few-Shot Learning for Multimodal Anxiety Detection	2025-11-10	Show Anxiety disorders impact millions globally, yet traditional diagnosis relies on clinical interviews, while machine learning models struggle with overfitting due to limited data. Large-scale data collection remains costly and time-consuming, restricting accessibility. To address this, we introduce the Hyperbolic Curvature Few-Shot Learning Network (HCFSLN), a novel Few-Shot Learning (FSL) framework for multimodal anxiety detection, integrating speech, physiological signals, and video data. HCFSLN enhances feature separability through hyperbolic embeddings, cross-modal attention, and an adaptive gating network, enabling robust classification with minimal data. We collected a multimodal anxiety dataset from 108 participants and benchmarked HCFSLN against six FSL baselines, achieving 88% accuracy, outperforming the best baseline by 14%. These results highlight the effectiveness of hyperbolic space for modeling anxiety-related speech patterns and demonstrate FSL's potential for anxiety classification.		None
Sentiment Analysis On YouTube Comments Using Machine Learning Techniques Based On Video Games Content	2025-11-10	Show The rapid evolution of the gaming industry, driven by technological advancements and a burgeoning community, necessitates a deeper understanding of user sentiments, especially as expressed on popular social media platforms like YouTube. This study presents a sentiment analysis on video games based on YouTube comments, aiming to understand user sentiments within the gaming community. Utilizing YouTube API, comments related to various video games were collected and analyzed using the TextBlob sentiment analysis tool. The pre-processed data underwent classification using machine learning algorithms, including Naïve Bayes, Logistic Regression, and Support Vector Machine (SVM). Among these, SVM demonstrated superior performance, achieving the highest classification accuracy across different datasets. The analysis spanned multiple popular gaming videos, revealing trends and insights into user preferences and critiques. The findings underscore the importance of advanced sentiment analysis in capturing the nuanced emotions expressed in user comments, providing valuable feedback for game developers to enhance game design and user experience. Future research will focus on integrating more sophisticated natural language processing techniques and exploring additional data sources to further refine sentiment analysis in the gaming domain.	6 pag... 6 pages, 7 figures, 2025 IEEE 9th International Conference on Software Engineering & Computer Systems	None
Sign language recognition from skeletal data using graph and recurrent neural networks	2025-11-08	Show This work presents an approach for recognizing isolated sign language gestures using skeleton-based pose data extracted from video sequences. A Graph-GRU temporal network is proposed to model both spatial and temporal dependencies between frames, enabling accurate classification. The model is trained and evaluated on the AUTSL (Ankara university Turkish sign language) dataset, achieving high accuracy. Experimental results demonstrate the effectiveness of integrating graph-based spatial representations with temporal modeling, providing a scalable framework for sign language recognition. The results of this approach highlight the potential of pose-driven methods for sign language understanding.	15 pages, 2 figures	None
On the Brittleness of CLIP Text Encoders	2025-11-07	Show Multimodal co-embedding models, especially CLIP, have advanced the state of the art in zero-shot classification and multimedia information retrieval in recent years by aligning images and text in a shared representation space. However, such modals trained on a contrastive alignment can lack stability towards small input perturbations. Especially when dealing with manually expressed queries, minor variations in the query can cause large differences in the ranking of the best-matching results. In this paper, we present a systematic analysis of the effect of multiple classes of non-semantic query perturbations in an multimedia information retrieval scenario. We evaluate a diverse set of lexical, syntactic, and semantic perturbations across multiple CLIP variants using the TRECVID Ad-Hoc Video Search queries and the V3C1 video collection. Across models, we find that syntactic and semantic perturbations drive the largest instabilities, while brittleness is concentrated in trivial surface edits such as punctuation and case. Our results highlight robustness as a critical dimension for evaluating vision-language models beyond benchmark accuracy.	Accep... Accepted for publication at MMM'26. Analysis code can be found here: https://github.com/allie-tran/clip-brittleness	Code Link
Dark Transformer: A Video Transformer for Action Recognition in the Dark	2025-11-07	Show Recognizing human actions in adverse lighting conditions presents significant challenges in computer vision, with wide-ranging applications in visual surveillance and nighttime driving. Existing methods tackle action recognition and dark enhancement separately, limiting the potential for end-to-end learning of spatiotemporal representations for video action classification. This paper introduces Dark Transformer, a novel video transformer-based approach for action recognition in low-light environments. Dark Transformer leverages spatiotemporal self-attention mechanisms in cross-domain settings to enhance cross-domain action recognition. By extending video transformers to learn cross-domain knowledge, Dark Transformer achieves state-of-the-art performance on benchmark action recognition datasets, including InFAR, XD145, and ARID. The proposed approach demonstrates significant promise in addressing the challenges of action recognition in adverse lighting conditions, offering practical implications for real-world applications.	8 Figures, 12 Pages	None
A Hybrid Deep Learning Model for Robust Biometric Authentication from Low-Frame-Rate PPG Signals	2025-11-06	Show Photoplethysmography (PPG) signals, which measure changes in blood volume in the skin using light, have recently gained attention in biometric authentication because of their non-invasive acquisition, inherent liveness detection, and suitability for low-cost wearable devices. However, PPG signal quality is challenged by motion artifacts, illumination changes, and inter-subject physiological variability, making robust feature extraction and classification crucial. This study proposes a lightweight and cost-effective biometric authentication framework based on PPG signals extracted from low-frame-rate fingertip videos. The CFIHSR dataset, comprising PPG recordings from 46 subjects at a sampling rate of 14 Hz, is employed for evaluation. The raw PPG signals undergo a standard preprocessing pipeline involving baseline drift removal, motion artifact suppression using Principal Component Analysis (PCA), bandpass filtering, Fourier-based resampling, and amplitude normalization. To generate robust representations, each one-dimensional PPG segment is converted into a two-dimensional time-frequency scalogram via the Continuous Wavelet Transform (CWT), effectively capturing transient cardiovascular dynamics. We developed a hybrid deep learning model, termed CVT-ConvMixer-LSTM, by combining spatial features from the Convolutional Vision Transformer (CVT) and ConvMixer branches with temporal features from a Long Short-Term Memory network (LSTM). The experimental results on 46 subjects demonstrate an authentication accuracy of 98%, validating the robustness of the model to noise and variability between subjects. Due to its efficiency, scalability, and inherent liveness detection capability, the proposed system is well-suited for real-world mobile and embedded biometric security applications.	This ... This work has been submitted to IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM) for possible publication	None
What Time Tells Us? An Explorative Study of Time Awareness Learned from Static Images	2025-11-06	Show Time becomes visible through illumination changes in what we see. Inspired by this, in this paper we explore the potential to learn time awareness from static images, trying to answer: what time tells us? To this end, we first introduce a Time-Oriented Collection (TOC) dataset, which contains 130,906 images with reliable timestamps. Leveraging this dataset, we propose a Time-Image Contrastive Learning (TICL) approach to jointly model timestamps and related visual representations through cross-modal contrastive learning. We found that the proposed TICL, 1) not only achieves state-of-the-art performance on the timestamp estimation task, over various benchmark metrics, 2) but also, interestingly, though only seeing static images, the time-aware embeddings learned from TICL show strong capability in several time-aware downstream tasks such as time-based image retrieval, video scene classification, and time-aware image editing. Our findings suggest that time-related visual cues can be learned from static images and are beneficial for various vision tasks, laying a foundation for future research on understanding time-related visual context. Project page: https://rathgrith.github.io/timetells_release/	Accep... Accepted by TMLR 2025	Code Link
From Coarse to Fine-Grained Emotion Annotation: An Immediate Recall Paradigm with Validation through Physiological Evidence and Recognition Performance	2025-11-05	Show Traditional video-induced emotion physiological datasets often use whole-trial annotation, assigning a single emotion label to all data collected during an entire trial. This coarse-grained annotation approach misaligns with the dynamic and temporally localized nature of emotional responses as they unfold with video narratives, introducing label noise that limits emotion recognition algorithm evaluation and performance. To solve the label noise problem caused by coarse-grained annotation, we propose a fine-grained annotation method through an immediate recall paradigm. This paradigm integrates an immediate video replay phase after the initial stimulus viewing, allowing participants to precisely mark the onset timestamp, emotion label, and intensity based on their immediate recall. We validate this paradigm through physiological evidence and recognition performance. Physiological validation of multimodal signals within participant-marked windows revealed rhythm-specific EEG patterns and arousal-dependent GSR responses-with SCRs appearing in 91% of high-arousal versus 6% of low-arousal emotion windows. These objective physiological data changes strongly aligned with subjective annotations, confirming annotation precision. For recognition performance, classification experiments showed that models trained on fine-grained annotations achieved 9.7% higher accuracy than traditional whole-trial labeling, despite using less data. This work not only addresses label noise through fine-grained annotation but also demonstrates that annotation precision outweighs data scale in determining emotion recognition performance.		None
Generative deep learning for foundational video translation in ultrasound	2025-11-05	Show Deep learning (DL) has the potential to revolutionize image acquisition and interpretation across medicine, however, attention to data imbalance and missingness is required. Ultrasound data presents a particular challenge because in addition to different views and structures, it includes several sub-modalities-such as greyscale and color flow doppler (CFD)-that are often imbalanced in clinical studies. Image translation can help balance datasets but is challenging for ultrasound sub-modalities to date. Here, we present a generative method for ultrasound CFD-greyscale video translation, trained on 54,975 videos and tested on 8,368. The method developed leveraged pixel-wise, adversarial, and perceptual loses and utilized two networks: one for reconstructing anatomic structures and one for denoising to achieve realistic ultrasound imaging. Average pairwise SSIM between synthetic videos and ground truth was 0.91+/-0.04. Synthetic videos performed indistinguishably from real ones in DL classification and segmentation tasks and when evaluated by blinded clinical experts: F1 score was 0.9 for real and 0.89 for synthetic videos; Dice score between real and synthetic segmentation was 0.97. Overall clinician accuracy in distinguishing real vs synthetic videos was 54+/-6% (42-61%), indicating realistic synthetic videos. Although trained only on heart videos, the model worked well on ultrasound spanning several clinical domains (average SSIM 0.91+/-0.05), demonstrating foundational abilities. Together, these data expand the utility of retrospectively collected imaging and augment the dataset design toolbox for medical imaging.		None
TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detection	2025-11-01	Show Video anomalies often depend on contextual information available and temporal evolution. Non-anomalous action in one context can be anomalous in some other context. Most anomaly detectors, however, do not notice this type of context, which seriously limits their capability to generalize to new, real-life situations. Our work addresses the context-aware zero-shot anomaly detection challenge, in which systems need to learn adaptively to detect new events by correlating temporal and appearance features with textual traces of memory in real time. Our approach defines a memory-augmented pipeline, correlating temporal signals with visual embeddings using cross-attention, and real-time zero-shot anomaly classification by contextual similarity scoring. We achieve 90.4% AUC on UCF-Crime and 83.67% AP on XD-Violence, a new state-of-the-art among zero-shot models. Our model achieves real-time inference with high precision and explainability for deployment. We show that, by fusing cross-attention temporal fusion and contextual memory, we achieve high fidelity anomaly detection, a step towards the applicability of zero-shot models in real-world surveillance and infrastructure monitoring.	10 pages, 5 figures	None
FeNN-DMA: A RISC-V SoC for SNN acceleration	2025-11-01	Show Spiking Neural Networks (SNNs) are a promising, energy-efficient alternative to standard Artificial Neural Networks (ANNs) and are particularly well-suited to spatio-temporal tasks such as keyword spotting and video classification. However, SNNs have a much lower arithmetic intensity than ANNs and are therefore not well-matched to standard accelerators like GPUs and TPUs. Field Programmable Gate Arrays(FPGAs) are designed for such memory-bound workloads and here we develop a novel, fully-programmable RISC-V-based system-on-chip (FeNN-DMA), tailored to simulating SNNs on modern UltraScale+ FPGAs. We show that FeNN-DMA has comparable resource usage and energy requirements to state-of-the-art fixed-function SNN accelerators, yet it is capable of simulating much larger and more complex models. Using this functionality, we demonstrate state-of-the-art classification accuracy on the Spiking Heidelberg Digits and Neuromorphic MNIST tasks.		None
Time Weaver: A Conditional Time Series Generation Model	2025-10-29	Show Imagine generating a city's electricity demand pattern based on weather, the presence of an electric vehicle, and location, which could be used for capacity planning during a winter freeze. Such real-world time series are often enriched with paired heterogeneous contextual metadata (e.g., weather and location). Current approaches to time series generation often ignore this paired metadata. Additionally, the heterogeneity in metadata poses several practical challenges in adapting existing conditional generation approaches from the image, audio, and video domains to the time series domain. To address this gap, we introduce TIME WEAVER, a novel diffusion-based model that leverages the heterogeneous metadata in the form of categorical, continuous, and even time-variant variables to significantly improve time series generation. Additionally, we show that naive extensions of standard evaluation metrics from the image to the time series domain are insufficient. These metrics do not penalize conditional generation approaches for their poor specificity in reproducing the metadata-specific features in the generated time series. Thus, we innovate a novel evaluation metric that accurately captures the specificity of conditional generation and the realism of the generated time series. We show that TIME WEAVER outperforms state-of-the-art benchmarks, such as Generative Adversarial Networks (GANs), by up to 30% in downstream classification tasks on real-world energy, medical, air quality, and traffic datasets.		None
Classification of Driver Behaviour Using External Observation Techniques for Autonomous Vehicles	2025-10-29	Show Road traffic accidents remain a significant global concern, with human error, particularly distracted and impaired driving, among the leading causes. This study introduces a novel driver behaviour classification system that uses external observation techniques to detect indicators of distraction and impairment. The proposed framework employs advanced computer vision methodologies, including real-time object tracking, lateral displacement analysis, and lane position monitoring. The system identifies unsafe driving behaviours such as excessive lateral movement and erratic trajectory patterns by implementing the YOLO object detection model and custom lane estimation algorithms. Unlike systems reliant on inter-vehicular communication, this vision-based approach enables behavioural analysis of non-connected vehicles. Experimental evaluations on diverse video datasets demonstrate the framework's reliability and adaptability across varying road and environmental conditions.		None
Pindrop it! Audio and Visual Deepfake Countermeasures for Robust Detection and Fine Grained-Localization	2025-10-26	Show The field of visual and audio generation is burgeoning with new state-of-the-art methods. This rapid proliferation of new techniques underscores the need for robust solutions for detecting synthetic content in videos. In particular, when fine-grained alterations via localized manipulations are performed in visual, audio, or both domains, these subtle modifications add challenges to the detection algorithms. This paper presents solutions for the problems of deepfake video classification and localization. The methods were submitted to the ACM 1M Deepfakes Detection Challenge, achieving the best performance in the temporal localization task and a top four ranking in the classification task for the TestA split of the evaluation dataset.		None
Multimodal Fusion and Interpretability in Human Activity Recognition: A Reproducible Framework for Sensor-Based Modeling	2025-10-25	Show The research presents a comprehensive framework for consolidating multimodal sensor data collected under naturalistic conditions, grounded in the Carnegie Mellon University Multi-Modal Activity Database (CMU-MMAC). Focusing on Subject 07-Brownie, the study investigates the entire processing pipeline, from data alignment and transformation to fusion method evaluation, interpretability, and modality contribution. A unified preprocessing pipeline is developed to temporally align heterogeneous video and audio data. Fusion is performed through resampling, grayscale conversion, segmentation, and feature standardization. Semantic richness is confirmed via heatmaps, spectrograms, and luminance time series, while frame-aligned waveform overlays demonstrate temporal consistency. Results indicate that late fusion yields the highest validation accuracy, followed by hybrid fusion, with early fusion performing the lowest. To assess the interpretability and discriminative power of audio and video in fused activity recognition, PCA and t-SNE visualize feature coherence over time. Classification results show limited performance for audio alone, moderate for video, and significant improvement with multimodal fusion, underscoring the strengths of combined data. Incorporating RFID data, which captures sparse interactions asynchronously, further enhances recognition accuracy by over 50% and improves macro-averaged ROC-AUC. The framework demonstrates the potential to transform raw, asynchronous sensor data into aligned, semantically meaningful representations, providing a reproducible approach for multimodal data integration and interpretation in intelligent systems designed to perceive complex human activities.	33 pa... 33 pages, 12 figures, 3 tables	None
A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings	2025-10-25	Show Content moderation research has recently made significant advances, but remains limited in serving the majority of the world's languages due to the lack of resources, leaving millions of vulnerable users to online hostility. This work presents a large-scale human-annotated multi-task benchmark dataset for abusive language detection in Tigrinya social media with joint annotations for three tasks: abusiveness, sentiment, and topic classification. The dataset comprises 13,717 YouTube comments annotated by nine native speakers, collected from 7,373 videos with a total of over 1.2 billion views across 51 channels. We developed an iterative term clustering approach for effective data selection. Recognizing that around 64% of Tigrinya social media content uses Romanized transliterations rather than native Ge'ez script, our dataset accommodates both writing systems to reflect actual language use. We establish strong baselines across the tasks in the benchmark, while leaving significant challenges for future contributions. Our experiments demonstrate that small fine-tuned models outperform prompted frontier large language models (LLMs) in the low-resource setting, achieving 86.67% F1 in abusiveness detection (7+ points over best LLM), and maintain stronger performance in all other tasks. The benchmark is made public to promote research on online safety.	Accep... Accepted at NeurIPS 2025	None
Cross-Enhanced Multimodal Fusion of Eye-Tracking and Facial Features for Alzheimer's Disease Diagnosis	2025-10-25	Show Accurate diagnosis of Alzheimer's disease (AD) is essential for enabling timely intervention and slowing disease progression. Multimodal diagnostic approaches offer considerable promise by integrating complementary information across behavioral and perceptual domains. Eye-tracking and facial features, in particular, are important indicators of cognitive function, reflecting attentional distribution and neurocognitive state. However, few studies have explored their joint integration for auxiliary AD diagnosis. In this study, we propose a multimodal cross-enhanced fusion framework that synergistically leverages eye-tracking and facial features for AD detection. The framework incorporates two key modules: (a) a Cross-Enhanced Fusion Attention Module (CEFAM), which models inter-modal interactions through cross-attention and global enhancement, and (b) a Direction-Aware Convolution Module (DACM), which captures fine-grained directional facial features via horizontal-vertical receptive fields. Together, these modules enable adaptive and discriminative multimodal representation learning. To support this work, we constructed a synchronized multimodal dataset, including 25 patients with AD and 25 healthy controls (HC), by recording aligned facial video and eye-tracking sequences during a visual memory-search paradigm, providing an ecologically valid resource for evaluating integration strategies. Extensive experiments on this dataset demonstrate that our framework outperforms traditional late fusion and feature concatenation methods, achieving a classification accuracy of 95.11% in distinguishing AD from HC, highlighting superior robustness and diagnostic performance by explicitly modeling inter-modal dependencies and modality-specific contributions.	35 pa... 35 pages, 8 figures, and 7 tables	None
Simplifying Knowledge Transfer in Pretrained Models	2025-10-25	Show Pretrained models are ubiquitous in the current deep learning landscape, offering strong results on a broad range of tasks. Recent works have shown that models differing in various design choices exhibit categorically diverse generalization behavior, resulting in one model grasping distinct data-specific insights unavailable to the other. In this paper, we propose to leverage large publicly available model repositories as an auxiliary source of model improvements. We introduce a data partitioning strategy where pretrained models autonomously adopt either the role of a student, seeking knowledge, or that of a teacher, imparting knowledge. Experiments across various tasks demonstrate the effectiveness of our proposed approach. In image classification, we improved the performance of ViT-B by approximately 1.4% through bidirectional knowledge transfer with ViT-T. For semantic segmentation, our method boosted all evaluation metrics by enabling knowledge transfer both within and across backbone architectures. In video saliency prediction, our approach achieved a new state-of-the-art. We further extend our approach to knowledge transfer between multiple models, leading to considerable performance improvements for all model participants.	12 pa... 12 pages, 3 figures, 6 tables, Accepted at TMLR 2025	None
egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-World Tasks	2025-10-25	Show Understanding affect is central to anticipating human behavior, yet current egocentric vision benchmarks largely ignore the person's emotional states that shape their decisions and actions. Existing tasks in egocentric perception focus on physical activities, hand-object interactions, and attention modeling - assuming neutral affect and uniform personality. This limits the ability of vision systems to capture key internal drivers of behavior. In this paper, we present egoEMOTION, the first dataset that couples egocentric visual and physiological signals with dense self-reports of emotion and personality across controlled and real-world scenarios. Our dataset includes over 50 hours of recordings from 43 participants, captured using Meta's Project Aria glasses. Each session provides synchronized eye-tracking video, headmounted photoplethysmography, inertial motion data, and physiological baselines for reference. Participants completed emotion-elicitation tasks and naturalistic activities while self-reporting their affective state using the Circumplex Model and Mikels' Wheel as well as their personality via the Big Five model. We define three benchmark tasks: (1) continuous affect classification (valence, arousal, dominance); (2) discrete emotion classification; and (3) trait-level personality inference. We show that a classical learning-based method, as a simple baseline in real-world affect prediction, produces better estimates from signals captured on egocentric vision systems than processing physiological signals. Our dataset establishes emotion and personality as core dimensions in egocentric perception and opens new directions in affect-driven modeling of behavior, intent, and interaction.	Accep... Accepted for publication at NeurIPS 2025	None
Human-Centric Anomaly Detection in Surveillance Videos Using YOLO-World and Spatio-Temporal Deep Learning	2025-10-24	Show Anomaly detection in surveillance videos remains a challenging task due to the diversity of abnormal events, class imbalance, and scene-dependent visual clutter. To address these issues, we propose a robust deep learning framework that integrates human-centric preprocessing with spatio-temporal modeling for multi-class anomaly classification. Our pipeline begins by applying YOLO-World - an open-vocabulary vision-language detector - to identify human instances in raw video clips, followed by ByteTrack for consistent identity-aware tracking. Background regions outside detected bounding boxes are suppressed via Gaussian blurring, effectively reducing scene-specific distractions and focusing the model on behaviorally relevant foreground content. The refined frames are then processed by an ImageNet-pretrained InceptionV3 network for spatial feature extraction, and temporal dynamics are captured using a bidirectional LSTM (BiLSTM) for sequence-level classification. Evaluated on a five-class subset of the UCF-Crime dataset (Normal, Burglary, Fighting, Arson, Explosion), our method achieves a mean test accuracy of 92.41% across three independent trials, with per-class F1-scores consistently exceeding 0.85. Comprehensive evaluation metrics - including confusion matrices, ROC curves, and macro/weighted averages - demonstrate strong generalization and resilience to class imbalance. The results confirm that foreground-focused preprocessing significantly enhances anomaly discrimination in real-world surveillance scenarios.		None
SPAN: Continuous Modeling of Suspicion Progression for Temporal Intention Localization	2025-10-24	Show Temporal Intention Localization (TIL) is crucial for video surveillance, focusing on identifying varying levels of suspicious intentions to improve security monitoring. However, existing discrete classification methods fail to capture the continuous nature of suspicious intentions, limiting early intervention and explainability. In this paper, we propose the Suspicion Progression Analysis Network (SPAN), which shifts from discrete classification to continuous regression, enabling the capture of fluctuating and evolving suspicious intentions. We reveal that suspicion exhibits long-term dependencies and cumulative effects, similar to Temporal Point Process (TPP) theory. Based on these insights, we define a suspicion score formula that models continuous changes while accounting for temporal characteristics. We also introduce Suspicion Coefficient Modulation, which adjusts suspicion coefficients using multimodal information to reflect the varying impacts of suspicious actions. Additionally, the Concept-Anchored Mapping method is proposed to link suspicious actions to predefined intention concepts, offering insights into both the actions and their potential underlying intentions. Extensive experiments on the HAI dataset show that SPAN significantly outperforms existing methods, reducing MSE by 19.8% and improving average mAP by 1.78%. Notably, SPAN achieves a 2.74% mAP gain in low-frequency cases, demonstrating its superior ability to capture subtle behavioral changes. Compared to discrete classification systems, our continuous suspicion modeling approach enables earlier detection and proactive intervention, greatly enhancing system explainability and practical utility in security applications.		None
VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models	2025-10-23	Show Foundation models have advanced computer vision by enabling strong performance across diverse tasks through large-scale pretraining and supervised fine-tuning. However, they may underperform in domains with distribution shifts and scarce labels, where supervised fine-tuning may be infeasible. While continued self-supervised learning for model adaptation is common for generative language models, this strategy has not proven effective for vision-centric encoder models. To address this challenge, we introduce a novel formulation of self-supervised fine-tuning for vision foundation models, where the model is adapted to a new domain without requiring annotations, leveraging only short multi-view object-centric videos. Our method is referred to as VESSA: Video-based objEct-centric Self-Supervised Adaptation for visual foundation models. VESSA's training technique is based on a self-distillation paradigm, where it is critical to carefully tune prediction heads and deploy parameter-efficient adaptation techniques - otherwise, the model may quickly forget its pretrained knowledge and reach a degraded state. VESSA benefits significantly from multi-view object observations sourced from different frames in an object-centric video, efficiently learning robustness to varied capture conditions, without the need of annotations. Through comprehensive experiments with 3 vision foundation models on 2 datasets, VESSA demonstrates consistent improvements in downstream classification tasks, compared to the base models and previous adaptation methods. Code is publicly available at https://github.com/jesimonbarreto/VESSA.	Confe... Conference on Neural Information Processing Systems (NeurIPS 2025)	Code Link
Breakdance Video classification in the age of Generative AI	2025-10-23	Show Large Vision Language models have seen huge application in several sports use-cases recently. Most of these works have been targeted towards a limited subset of popular sports like soccer, cricket, basketball etc; focusing on generative tasks like visual question answering, highlight generation. This work analyzes the applicability of the modern video foundation models (both encoder and decoder) for a very niche but hugely popular dance sports - breakdance. Our results show that Video Encoder models continue to outperform state-of-the-art Video Language Models for prediction tasks. We provide insights on how to choose the encoder model and provide a thorough analysis into the workings of a finetuned decoder model for breakdance video classification.	11 pages	None
8-Calves Image dataset	2025-10-22	Show Automated livestock monitoring is crucial for precision farming, but robust computer vision models are hindered by a lack of datasets reflecting real-world group challenges. We introduce the 8-Calves dataset, a challenging benchmark for multi-animal detection, tracking, and identification. It features a one-hour video of eight Holstein Friesian calves in a barn, with frequent occlusions, motion blur, and diverse poses. A semi-automated pipeline using a fine-tuned YOLOv8 detector and ByteTrack, followed by manual correction, provides over 537,000 bounding boxes with temporal identity labels. We benchmark 28 object detectors, showing near-perfect performance on a lenient IoU threshold (mAP50: 95.2-98.9%) but significant divergence on stricter metrics (mAP50:95: 56.5-66.4%), highlighting fine-grained localization challenges. Our identification benchmark across 23 models reveals a trade-off: scaling model size improves classification accuracy but compromises retrieval. Smaller architectures like ConvNextV2 Nano achieve the best balance (73.35% accuracy, 50.82% Top-1 KNN). Pre-training focused on semantic learning (e.g., BEiT) yielded superior transferability. For tracking, leading methods achieve high detection accuracy (MOTA > 0.92) but struggle with identity preservation (IDF1 $\approx$ 0.27), underscoring a key challenge in occlusion-heavy scenarios. The 8-Calves dataset bridges a gap by providing temporal richness and realistic challenges, serving as a resource for advancing agricultural vision models. The dataset and code are available at https://huggingface.co/datasets/tonyFang04/8-calves.	16 pages, 5 figures	None
kabr-tools: Automated Framework for Multi-Species Behavioral Monitoring	2025-10-22	Show A comprehensive understanding of animal behavior ecology depends on scalable approaches to quantify and interpret complex, multidimensional behavioral patterns. Traditional field observations are often limited in scope, time-consuming, and labor-intensive, hindering the assessment of behavioral responses across landscapes. To address this, we present kabr-tools (Kenyan Animal Behavior Recognition Tools), an open-source package for automated multi-species behavioral monitoring. This framework integrates drone-based video with machine learning systems to extract behavioral, social, and spatial metrics from wildlife footage. Our pipeline leverages object detection, tracking, and behavioral classification systems to generate key metrics, including time budgets, behavioral transitions, social interactions, habitat associations, and group composition dynamics. Compared to ground-based methods, drone-based observations significantly improved behavioral granularity, reducing visibility loss by 15% and capturing more transitions with higher accuracy and continuity. We validate kabr-tools through three case studies, analyzing 969 behavioral sequences, surpassing the capacity of traditional methods for data capture and annotation. We found that, like Plains zebras, vigilance in Grevy's zebras decreases with herd size, but, unlike Plains zebras, habitat has a negligible impact. Plains and Grevy's zebras exhibit strong behavioral inertia, with rare transitions to alert behaviors and observed spatial segregation between Grevy's zebras, Plains zebras, and giraffes in mixed-species herds. By enabling automated behavioral monitoring at scale, kabr-tools offers a powerful tool for ecosystem-wide studies, advancing conservation, biodiversity research, and ecological monitoring.	31 pages	None
Preliminary Use of Vision Language Model Driven Extraction of Mouse Behavior Towards Understanding Fear Expression	2025-10-22	Show Integration of diverse data will be a pivotal step towards improving scientific explorations in many disciplines. This work establishes a vision-language model (VLM) that encodes videos with text input in order to classify various behaviors of a mouse existing in and engaging with their environment. Importantly, this model produces a behavioral vector over time for each subject and for each session the subject undergoes. The output is a valuable dataset that few programs are able to produce with as high accuracy and with minimal user input. Specifically, we use the open-source Qwen2.5-VL model and enhance its performance through prompts, in-context learning (ICL) with labeled examples, and frame-level preprocessing. We found that each of these methods contributes to improved classification, and that combining them results in strong F1 scores across all behaviors, including rare classes like freezing and fleeing, without any model fine-tuning. Overall, this model will support interdisciplinary researchers studying mouse behavior by enabling them to integrate diverse behavioral features, measured across multiple time points and environments, into a comprehensive dataset that can address complex research questions.		None
Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space	2025-10-20	Show Given a video with $T$ frames, frame sampling is a task to select $N \ll T$ frames, so as to maximize the performance of a fixed video classifier. Not just brute-force search, but most existing methods suffer from its vast search space of $\binom{T}{N}$, especially when $N$ gets large. To address this challenge, we introduce a novel perspective of reducing the search space from $O(T^N)$ to $O(T)$. Instead of exploring the entire $O(T^N)$ space, our proposed semi-optimal policy selects the top $N$ frames based on the independently estimated value of each frame using per-frame confidence, significantly reducing the computational complexity. We verify that our semi-optimal policy can efficiently approximate the optimal policy, particularly under practical settings. Additionally, through extensive experiments on various datasets and model architectures, we demonstrate that learning our semi-optimal policy ensures stable and high performance regardless of the size of $N$ and $T$.		None
ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy	2025-10-20	Show We present ManzaiSet, the first large scale multimodal dataset of viewer responses to Japanese manzai comedy, capturing facial videos and audio from 241 participants watching up to 10 professional performances in randomized order (94.6 percent watched >= 8; analyses focus on n=228). This addresses the Western centric bias in affective computing. Three key findings emerge: (1) k means clustering identified three distinct viewer types: High and Stable Appreciators (72.8 percent, n=166), Low and Variable Decliners (13.2 percent, n=30), and Variable Improvers (14.0 percent, n=32), with heterogeneity of variance (Brown Forsythe p < 0.001); (2) individual level analysis revealed a positive viewing order effect (mean slope = 0.488, t(227) = 5.42, p < 0.001, permutation p < 0.001), contradicting fatigue hypotheses; (3) automated humor classification (77 instances, 131 labels) plus viewer level response modeling found no type wise differences after FDR correction. The dataset enables culturally aware emotion AI development and personalized entertainment systems tailored to non Western contexts.	ICCV ... ICCV 2025 Workshop on Affective & Behavior Analysis in-the-Wild (ABAW), Honolulu, HI, USA (Oct 19, 2025, HST). 11 pages, 5 figures	None
Frugal Federated Learning for Violence Detection: A Comparison of LoRA-Tuned VLMs and Personalized CNNs	2025-10-20	Show We examine frugal federated learning approaches to violence detection by comparing two complementary strategies: (i) zero-shot and federated fine-tuning of vision-language models (VLMs), and (ii) personalized training of a compact 3D convolutional neural network (CNN3D). Using LLaVA-7B and a 65.8M parameter CNN3D as representative cases, we evaluate accuracy, calibration, and energy usage under realistic non-IID settings. Both approaches exceed 90% accuracy. CNN3D slightly outperforms Low-Rank Adaptation(LoRA)-tuned VLMs in ROC AUC and log loss, while using less energy. VLMs remain favorable for contextual reasoning and multimodal inference. We quantify energy and CO$_2$ emissions across training and inference, and analyze sustainability trade-offs for deployment. To our knowledge, this is the first comparative study of LoRA-tuned vision-language models and personalized CNNs for federated violence detection, with an emphasis on energy efficiency and environmental metrics. These findings support a hybrid model: lightweight CNNs for routine classification, with selective VLM activation for complex or descriptive scenarios. The resulting framework offers a reproducible baseline for responsible, resource-aware AI in video surveillance, with extensions toward real-time, multimodal, and lifecycle-aware systems.	7 pag... 7 pages, 1 figure, FLTA 2025	None
ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification	2025-10-20	Show Differentiating cardiogenic pulmonary oedema (CPE) from non-cardiogenic and structurally normal lungs in lung ultrasound (LUS) videos remains challenging due to the high visual variability of non-cardiogenic inflammatory patterns (NCIP/ARDS-like), interstitial lung disease, and healthy lungs. This heterogeneity complicates automated classification as overlapping B-lines and pleural artefacts are common. We introduce ZACH-ViT (Zero-token Adaptive Compact Hierarchical Vision Transformer), a 0.25 M-parameter Vision Transformer variant that removes both positional embeddings and the [CLS] token, making it fully permutation-invariant and suitable for unordered medical image data. To enhance generalization, we propose ShuffleStrides Data Augmentation (SSDA), which permutes probe-view sequences and frame orders while preserving anatomical validity. ZACH-ViT was evaluated on 380 LUS videos from 95 critically ill patients against nine state-of-the-art baselines. Despite the heterogeneity of the non-cardiogenic group, ZACH-ViT achieved the highest validation and test ROC-AUC (0.80 and 0.79) with balanced sensitivity (0.60) and specificity (0.91), while all competing models collapsed to trivial classification. It trains 1.35x faster than Minimal ViT (0.62M parameters) with 2.5x fewer parameters, supporting real-time clinical deployment. These results show that aligning architectural design with data structure can outperform scale in small-data medical imaging.	14 pa... 14 pages, 6 figures, 2 tables. Primary subject: cs.LG (Machine Learning) Cross-listed to: cs.CV (Computer Vision and Pattern Recognition), eess.IV (Image and Video Processing). Code available at: https://github.com/Bluesman79/ZACH-ViT Installation: pip install zachvit Paper licensed under CC BY-NC-ND 4.0. Code released under Apache 2.0 License	Code Link
ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment	2025-10-19	Show We address the task of zero-shot video classification for extremely fine-grained actions (e.g., Windmill Dunk in basketball), where no video examples or temporal annotations are available for unseen classes. While image-language models (e.g., CLIP, SigLIP) show strong open-set recognition, they lack temporal modeling needed for video understanding. We propose ActAlign, a truly zero-shot, training-free method that formulates video classification as a sequence alignment problem, preserving the generalization strength of pretrained image-language models. For each class, a large language model (LLM) generates an ordered sequence of sub-actions, which we align with video frames using Dynamic Time Warping (DTW) in a shared embedding space. Without any video-text supervision or fine-tuning, ActAlign achieves 30.5% accuracy on ActionAtlas--the most diverse benchmark of fine-grained actions across multiple sports--where human performance is only 61.6%. ActAlign outperforms billion-parameter video-language models while using 8x fewer parameters. Our approach is model-agnostic and domain-general, demonstrating that structured language priors combined with classical alignment methods can unlock the open-set recognition potential of image-language models for fine-grained video understanding.	Accep... Accepted to TMLR 2025 - Project page: https://amir-aghdam.github.io/act-align/	Code Link
DGME-T: Directional Grid Motion Encoding for Transformer-Based Historical Camera Movement Classification	2025-10-17	Show Camera movement classification (CMC) models trained on contemporary, high-quality footage often degrade when applied to archival film, where noise, missing frames, and low contrast obscure motion cues. We bridge this gap by assembling a unified benchmark that consolidates two modern corpora into four canonical classes and restructures the HISTORIAN collection into five balanced categories. Building on this benchmark, we introduce DGME-T, a lightweight extension to the Video Swin Transformer that injects directional grid motion encoding, derived from optical flow, via a learnable and normalised late-fusion layer. DGME-T raises the backbone's top-1 accuracy from 81.78% to 86.14% and its macro F1 from 82.08% to 87.81% on modern clips, while still improving the demanding World-War-II footage from 83.43% to 84.62% accuracy and from 81.72% to 82.63% macro F1. A cross-domain study further shows that an intermediate fine-tuning stage on modern data increases historical performance by more than five percentage points. These results demonstrate that structured motion priors and transformer representations are complementary and that even a small, carefully calibrated motion head can substantially enhance robustness in degraded film analysis. Related resources are available at https://github.com/linty5/DGME-T.	9 pag... 9 pages, accepted at ACMMM2025 SUMAC	Code Link
GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery	2025-10-17	Show Large Language Models (LLMs) show strong reasoning and text generation capabilities, prompting their use in scientific literature analysis, including novelty assessment. While evaluating novelty of scientific papers is crucial for peer review, it requires extensive knowledge of related work, something not all reviewers have. While recent work on LLM-assisted scientific literature analysis supports literature comparison, existing approaches offer limited transparency and lack mechanisms for result traceability via an information retrieval module. To address this gap, we introduce $\textbf{GraphMind}$, an easy-to-use interactive web tool designed to assist users in evaluating the novelty of scientific papers or drafted ideas. Specially, $\textbf{GraphMind}$ enables users to capture the main structure of a scientific paper, explore related ideas through various perspectives, and assess novelty via providing verifiable contextual insights. $\textbf{GraphMind}$ enables users to annotate key elements of a paper, explore related papers through various relationships, and assess novelty with contextual insight. This tool integrates external APIs such as arXiv and Semantic Scholar with LLMs to support annotation, extraction, retrieval and classification of papers. This combination provides users with a rich, structured view of a scientific idea's core contributions and its connections to existing work. $\textbf{GraphMind}$ is available at https://oyarsa.github.io/graphmind and a demonstration video at https://youtu.be/wKbjQpSvwJg. The source code is available at https://github.com/oyarsa/graphmind.	9 pag... 9 pages, 6 figures, 3 tables, EMNLP 2025 Demo paper	Code Link
Adaptive transfer learning for surgical tool presence detection in laparoscopic videos through gradual freezing fine-tuning	2025-10-17	Show Minimally invasive surgery can benefit significantly from automated surgical tool detection, enabling advanced analysis and assistance. However, the limited availability of annotated data in surgical settings poses a challenge for training robust deep learning models. This paper introduces a novel staged adaptive fine-tuning approach consisting of two steps: a linear probing stage to condition additional classification layers on a pre-trained CNN-based architecture and a gradual freezing stage to dynamically reduce the fine-tunable layers, aiming to regulate adaptation to the surgical domain. This strategy reduces network complexity and improves efficiency, requiring only a single training loop and eliminating the need for multiple iterations. We validated our method on the Cholec80 dataset, employing CNN architectures (ResNet-50 and DenseNet-121) pre-trained on ImageNet for detecting surgical tools in cholecystectomy endoscopic videos. Our results demonstrate that our method improves detection performance compared to existing approaches and established fine-tuning techniques, achieving a mean average precision (mAP) of 96.4%. To assess its broader applicability, the generalizability of the fine-tuning strategy was further confirmed on the CATARACTS dataset, a distinct domain of minimally invasive ophthalmic surgery. These findings suggest that gradual freezing fine-tuning is a promising technique for improving tool presence detection in diverse surgical procedures and may have broader applications in general image classification tasks.		None
SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians	2025-10-17	Show Accurate, real-time 3D reconstruction of human heads from monocular images and videos underlies numerous visual applications. As 3D ground truth data is hard to come by at scale, previous methods have sought to learn from abundant 2D videos in a self-supervised manner. Typically, this involves the use of differentiable mesh rendering, which is effective but faces limitations. To improve on this, we propose SHeaP (Self-supervised Head Geometry Predictor Learned via 2D Gaussians). Given a source image, we predict a 3DMM mesh and a set of Gaussians that are rigged to this mesh. We then reanimate this rigged head avatar to match a target frame, and backpropagate photometric losses to both the 3DMM and Gaussian prediction networks. We find that using Gaussians for rendering substantially improves the effectiveness of this self-supervised approach. Training solely on 2D data, our method surpasses existing self-supervised approaches in geometric evaluations on the NoW benchmark for neutral faces and a new benchmark for non-neutral expressions. Our method also produces highly expressive meshes, outperforming state-of-the-art in emotion classification.	For v... For video demonstrations and additional materials please see https://nlml.github.io/sheap/	Code Link
FERA: Foil Fencing Referee Assistant Using Pose-Based Multi-Label Move Recognition and Rule Reasoning	2025-10-16	Show The sport of fencing, like many other sports, faces challenges in refereeing: subjective calls, human errors, bias, and limited availability in practice environments. We present FERA (Fencing Referee Assistant), a prototype AI referee for foil fencing which integrates pose-based multi-label action recognition and rule-based reasoning. FERA extracts 2D joint positions from video, normalizes them, computes a 101-dimensional kinematic feature set, and applies a Transformer for multi-label move and blade classification. To determine priority and scoring, FERA applies a distilled language model with encoded right-of-way rules, producing both a decision and an explanation for each exchange. With limited hand-labeled data, a 5-fold cross-validation achieves an average macro-F1 score of 0.549, outperforming multiple baselines, including a Temporal Convolutional Network (TCN), BiLSTM, and a vanilla Transformer. While not ready for deployment, these results demonstrate a promising path towards automated referee assistance in foil fencing and new opportunities for AI applications, such as coaching in the field of fencing.	Updat... Updated author affiliation and contact information	None
Big Data Approaches to Bovine Bioacoustics: A FAIR-Compliant Dataset and Scalable ML Framework for Precision Livestock Welfare	2025-10-16	Show The convergence of IoT sensing, edge computing, and machine learning is transforming precision livestock farming. Yet bioacoustic data streams remain underused because of computational complexity and ecological validity challenges. We present one of the most comprehensive bovine vocalization datasets to date, with 569 curated clips covering 48 behavioral classes, recorded across three commercial dairy farms using multiple microphone arrays and expanded to 2900 samples through domain informed augmentation. This FAIR compliant resource addresses major Big Data challenges - volume (90 hours of recordings, 65.6 GB), variety (multi farm and multi zone acoustics), velocity (real time processing), and veracity (noise robust feature extraction). Our distributed processing framework integrates advanced denoising using iZotope RX, multimodal synchronization through audio and video alignment, and standardized feature engineering with 24 acoustic descriptors generated from Praat, librosa, and openSMILE. Preliminary benchmarks reveal distinct class level acoustic patterns for estrus detection, distress classification, and maternal communication. The datasets ecological realism, reflecting authentic barn acoustics rather than controlled settings, ensures readiness for field deployment. This work establishes a foundation for animal centered AI, where bioacoustic data enable continuous and non invasive welfare assessment at industrial scale. By releasing standardized pipelines and detailed metadata, we promote reproducible research that connects Big Data analytics, sustainable agriculture, and precision livestock management. The framework supports UN SDG 9, showing how data science can turn traditional farming into intelligent, welfare optimized systems that meet global food needs while upholding ethical animal care.	40 pa... 40 pages, 14 figures, 9 Tables	None
Camera Movement Classification in Historical Footage: A Comparative Study of Deep Video Models	2025-10-16	Show Camera movement conveys spatial and narrative information essential for understanding video content. While recent camera movement classification (CMC) methods perform well on modern datasets, their generalization to historical footage remains unexplored. This paper presents the first systematic evaluation of deep video CMC models on archival film material. We summarize representative methods and datasets, highlighting differences in model design and label definitions. Five standard video classification models are assessed on the HISTORIAN dataset, which includes expert-annotated World War II footage. The best-performing model, Video Swin Transformer, achieves 80.25% accuracy, showing strong convergence despite limited training data. Our findings highlight the challenges and potential of adapting existing models to low-quality video and motivate future work combining diverse input modalities and temporal architectures.	5 pag... 5 pages, accepted at AIROV2025	None
Synchronization of Multiple Videos	2025-10-15	Show Synchronizing videos captured simultaneously from multiple cameras in the same scene is often easy and typically requires only simple time shifts. However, synchronizing videos from different scenes or, more recently, generative AI videos, poses a far more complex challenge due to diverse subjects, backgrounds, and nonlinear temporal misalignment. We propose Temporal Prototype Learning (TPL), a prototype-based framework that constructs a shared, compact 1D representation from high-dimensional embeddings extracted by any of various pretrained models. TPL robustly aligns videos by learning a unified prototype sequence that anchors key action phases, thereby avoiding exhaustive pairwise matching. Our experiments show that TPL improves synchronization accuracy, efficiency, and robustness across diverse datasets, including fine-grained frame retrieval and phase classification tasks. Importantly, TPL is the first approach to mitigate synchronization issues in multiple generative AI videos depicting the same action. Our code and a new multiple video synchronization dataset are available at https://bgu-cs-vil.github.io/TPL/	ICCV 2025	Code Link
Scaling Vision Transformers for Functional MRI with Flat Maps	2025-10-15	Show A key question for adapting modern deep learning architectures to functional MRI (fMRI) is how to represent the data for model input. To bridge the modality gap between fMRI and natural images, we transform the 4D volumetric fMRI data into videos of 2D fMRI activity flat maps. We train Vision Transformers on 2.3K hours of fMRI flat map videos from the Human Connectome Project using the spatiotemporal masked autoencoder (MAE) framework. We observe that masked fMRI modeling performance improves with dataset size according to a strict power scaling law. Downstream classification benchmarks show that our model learns rich representations supporting both fine-grained state decoding across subjects, as well as subject-specific trait decoding across changes in brain state. This work is part of an ongoing open science project to build foundation models for fMRI data. Our code and datasets are available at https://github.com/MedARC-AI/fmri-fm.	NeurI... NeurIPS 2025 Workshop, Foundation Models for the Brain and Body; Code: https://github.com/MedARC-AI/fmri-fm; Discord: https://discord.gg/tVR4TWnRM9	Code Link
ESG-Net: Event-Aware Semantic Guided Network for Dense Audio-Visual Event Localization	2025-10-15	Show Dense audio-visual event localization (DAVE) aims to identify event categories and locate the temporal boundaries in untrimmed videos. Most studies only employ event-related semantic constraints on the final outputs, lacking cross-modal semantic bridging in intermediate layers. This causes modality semantic gap for further fusion, making it difficult to distinguish between event-related content and irrelevant background content. Moreover, they rarely consider the correlations between events, which limits the model to infer concurrent events among complex scenarios. In this paper, we incorporate multi-stage semantic guidance and multi-event relationship modeling, which respectively enable hierarchical semantic understanding of audio-visual events and adaptive extraction of event dependencies, thereby better focusing on event-related information. Specifically, our eventaware semantic guided network (ESG-Net) includes a early semantics interaction (ESI) module and a mixture of dependency experts (MoDE) module. ESI applys multi-stage semantic guidance to explicitly constrain the model in learning semantic information through multi-modal early fusion and several classification loss functions, ensuring hierarchical understanding of event-related content. MoDE promotes the extraction of multi-event dependencies through multiple serial mixture of experts with adaptive weight allocation. Extensive experiments demonstrate that our method significantly surpasses the state-of-the-art methods, while greatly reducing parameters and computational load. Our code will be released on https://github.com/uchiha99999/ESG-Net.		Code Link
Probabilistic Temporal Masked Attention for Cross-view Online Action Detection	2025-10-14	Show As a critical task in video sequence classification within computer vision, Online Action Detection (OAD) has garnered significant attention. The sensitivity of mainstream OAD models to varying video viewpoints often hampers their generalization when confronted with unseen sources. To address this limitation, we propose a novel Probabilistic Temporal Masked Attention (PTMA) model, which leverages probabilistic modeling to derive latent compressed representations of video frames in a cross-view setting. The PTMA model incorporates a GRU-based temporal masked attention (TMA) cell, which leverages these representations to effectively query the input video sequence, thereby enhancing information interaction and facilitating autoregressive frame-level video analysis. Additionally, multi-view information can be integrated into the probabilistic modeling to facilitate the extraction of view-invariant features. Experiments conducted under three evaluation protocols: cross-subject (cs), cross-view (cv), and cross-subject-view (csv) show that PTMA achieves state-of-the-art performance on the DAHLIA, IKEA ASM, and Breakfast datasets.	12 pa... 12 pages, 6 figures, accepted at IEEE Transactions on Multimedia (TMM), in press	None
Towards Cybersickness Severity Classification from VR Gameplay Videos Using Transfer Learning and Temporal Modeling	2025-10-14	Show With the rapid advancement of virtual reality (VR) technology, its adoption across domains such as healthcare, education, and entertainment has grown significantly. However, the persistent issue of cybersickness, marked by symptoms resembling motion sickness, continues to hinder widespread acceptance of VR. While recent research has explored multimodal deep learning approaches leveraging data from integrated VR sensors like eye and head tracking, there remains limited investigation into the use of video-based features for predicting cybersickness. In this study, we address this gap by utilizing transfer learning to extract high-level visual features from VR gameplay videos using the InceptionV3 model pretrained on the ImageNet dataset. These features are then passed to a Long Short-Term Memory (LSTM) network to capture the temporal dynamics of the VR experience and predict cybersickness severity over time. Our approach effectively leverages the time-series nature of video data, achieving a 68.4% classification accuracy for cybersickness severity. This surpasses the performance of existing models trained solely on video data, providing a practical tool for VR developers to evaluate and mitigate cybersickness in virtual environments. Furthermore, this work lays the foundation for future research on video-based temporal modeling for enhancing user comfort in VR applications.		None
Deep Attention-guided Adaptive Subsampling	2025-10-14	Show Although deep neural networks have provided impressive gains in performance, these improvements often come at the cost of increased computational complexity and expense. In many cases, such as 3D volume or video classification tasks, not all slices or frames are necessary due to inherent redundancies. To address this issue, we propose a novel learnable subsampling framework that can be integrated into any neural network architecture. Subsampling, being a nondifferentiable operation, poses significant challenges for direct adaptation into deep learning models. While some works, have proposed solutions using the Gumbel-max trick to overcome the problem of non-differentiability, they fall short in a crucial aspect: they are only task-adaptive and not inputadaptive. Once the sampling mechanism is learned, it remains static and does not adjust to different inputs, making it unsuitable for real-world applications. To this end, we propose an attention-guided sampling module that adapts to inputs even during inference. This dynamic adaptation results in performance gains and reduces complexity in deep neural network models. We demonstrate the effectiveness of our method on 3D medical imaging datasets from MedMNIST3D as well as two ultrasound video datasets for classification tasks, one of them being a challenging in-house dataset collected under real-world clinical conditions.		None
State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding	2025-10-14	Show Recently, pre-trained state space models have shown great potential for video classification, which sequentially compresses visual tokens in videos with linear complexity, thereby improving the processing efficiency of video data while maintaining high performance. To apply powerful pre-trained models to downstream tasks, prompt learning is proposed to achieve efficient downstream task adaptation with only a small number of fine-tuned parameters. However, the sequentially compressed visual prompt tokens fail to capture the spatial and temporal contextual information in the video, thus limiting the effective propagation of spatial information within a video frame and temporal information between frames in the state compression model and the extraction of discriminative information. To tackle the above issue, we proposed a State Space Prompting (SSP) method for video understanding, which combines intra-frame and inter-frame prompts to aggregate and propagate key spatiotemporal information in the video. Specifically, an Intra-Frame Gathering (IFG) module is designed to aggregate spatial key information within each frame. Besides, an Inter-Frame Spreading (IFS) module is designed to spread discriminative spatio-temporal information across different frames. By adaptively balancing and compressing key spatio-temporal information within and between frames, our SSP effectively propagates discriminative information in videos in a complementary manner. Extensive experiments on four video benchmark datasets verify that our SSP significantly outperforms existing SOTA methods by 2.76% on average while reducing the overhead of fine-tuning parameters.		None
Open Vocabulary Multi-Label Video Classification	2025-10-13	Show Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to open vocabulary single label action classification in videos. However, previous methods fall short in holistic video understanding which requires the ability to simultaneously recognize multiple actions and entities e.g., objects in the video in an open vocabulary setting. We formulate this problem as open vocabulary multilabel video classification and propose a method to adapt a pre-trained VLM such as CLIP to solve this task. We leverage large language models (LLMs) to provide semantic guidance to the VLM about class labels to improve its open vocabulary performance with two key contributions. First, we propose an end-to-end trainable architecture that learns to prompt an LLM to generate soft attributes for the CLIP text-encoder to enable it to recognize novel classes. Second, we integrate a temporal modeling module into CLIP's vision encoder to effectively model the spatio-temporal dynamics of video concepts as well as propose a novel regularized finetuning technique to ensure strong open vocabulary classification performance in the video domain. Our extensive experimentation showcases the efficacy of our approach on multiple benchmark datasets.	Accep... Accepted at ECCV 2024	None
Exploring Facial Biomarkers for Depression through Temporal Analysis of Action Units	2025-10-13	Show Depression is characterized by persistent sadness and loss of interest, significantly impairing daily functioning and now a widespread mental disorder. Traditional diagnostic methods rely on subjective assessments, necessitating objective approaches for accurate diagnosis. Our study investigates the use of facial action units (AUs) and emotions as biomarkers for depression. We analyzed facial expressions from video data of participants classified with or without depression. Our methodology involved detailed feature extraction, mean intensity comparisons of key AUs, and the application of time series classification models. Furthermore, we employed Principal Component Analysis (PCA) and various clustering algorithms to explore the variability in emotional expression patterns. Results indicate significant differences in the intensities of AUs associated with sadness and happiness between the groups, highlighting the potential of facial analysis in depression assessment.	Updated Authors	None
Investigating Identity Signals in Conversational Facial Dynamics via Disentangled Expression Features	2025-10-13	Show This work investigates whether individuals can be identified solely through the pure dynamical components of their facial expressions, independent of static facial appearance. We leverage the FLAME 3D morphable model to achieve explicit disentanglement between facial shape and expression dynamics, extracting frame-by-frame parameters from conversational videos while retaining only expression and jaw coefficients. On the CANDOR dataset of 1,429 speakers in naturalistic conversations, our Conformer model with supervised contrastive learning achieves 61.14%accuracy on 1,429-way classification -- 458 times above chance -- demonstrating that facial dynamics carry strong identity signatures. We introduce a drift-to-noise ratio (DNR) that quantifies the reliability of shape expression separation by measuring across-session shape changes relative to within-session variability. DNR strongly negatively correlates with recognition performance, confirming that unstable shape estimation compromises dynamic identification. Our findings reveal person-specific signatures in conversational facial dynamics, with implications for social perception and clinical assessment.		None
Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos	2025-10-13	Show The recent growth in the consumption of online media by children during early childhood necessitates data-driven tools enabling educators to filter out appropriate educational content for young learners. This paper presents an approach for detecting educational content in online videos. We focus on two widely used educational content classes: literacy and math. For each class, we choose prominent codes (sub-classes) based on the Common Core Standards. For example, literacy codes include letter names', letter sounds', and math codes include counting', sorting'. We pose this as a fine-grained multilabel classification problem as videos can contain multiple types of educational content and the content classes can get visually similar (e.g., letter names' vs letter sounds'). We propose a novel class prototypes based supervised contrastive learning approach that can handle fine-grained samples associated with multiple labels. We learn a class prototype for each class and a loss function is employed to minimize the distances between a class prototype and the samples from the class. Similarly, distances between a class prototype and the samples from other classes are maximized. As the alignment between visual and audio cues are crucial for effective comprehension, we consider a multimodal transformer network to capture the interaction between visual and audio cues in videos while learning the embedding for videos. For evaluation, we present a dataset, APPROVE, employing educational videos from YouTube labeled with fine-grained education classes by education researchers. APPROVE consists of 193 hours of expert-annotated videos with 19 classes. The proposed approach outperforms strong baselines on APPROVE and other benchmarks such as Youtube-8M, and COIN. The dataset is available at https://github.com/rohit-gupta/MMContrast/tree/main/APPROVE	Publi... Published at CVPR 2023	Code Link
Mixup Helps Understanding Multimodal Video Better	2025-10-13	Show Multimodal video understanding plays a crucial role in tasks such as action recognition and emotion classification by combining information from different modalities. However, multimodal models are prone to overfitting strong modalities, which can dominate learning and suppress the contributions of weaker ones. To address this challenge, we first propose Multimodal Mixup (MM), which applies the Mixup strategy at the aggregated multimodal feature level to mitigate overfitting by generating virtual feature-label pairs. While MM effectively improves generalization, it treats all modalities uniformly and does not account for modality imbalance during training. Building on MM, we further introduce Balanced Multimodal Mixup (B-MM), which dynamically adjusts the mixing ratios for each modality based on their relative contributions to the learning objective. Extensive experiments on several datasets demonstrate the effectiveness of our methods in improving generalization and multimodal robustness.		None
SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance	2025-10-13	Show Low signal-to-noise ratio videos -- such as those from underwater sonar, ultrasound, and microscopy -- pose significant challenges for computer vision models, particularly when paired clean imagery is unavailable. We present Spatiotemporal Augmentations and denoising in Video for Downstream Tasks (SAVeD), a novel self-supervised method that denoises low-SNR sensor videos using only raw noisy data. By leveraging distinctions between foreground and background motion and exaggerating objects with stronger motion signal, SAVeD enhances foreground object visibility and reduces background and camera noise without requiring clean video. SAVeD has a set of architectural optimizations that lead to faster throughput, training, and inference than existing deep learning methods. We also introduce a new denoising metric, FBD, which indicates foreground-background divergence for detection datasets without requiring clean imagery. Our approach achieves state-of-the-art results for classification, detection, tracking, and counting tasks, and it does so with fewer training resource requirements than existing deep-learning-based denoising methods. Project page: https://suzanne-stathatos.github.io/SAVeD Code page: https://github.com/suzanne-stathatos/SAVeD	Proje... Project page: https://suzanne-stathatos.github.io/SAVeD Code page: https://github.com/suzanne-stathatos/SAVeD	Code Link
Scaling Traffic Insights with AI and Language Model-Powered Camera Systems for Data-Driven Transportation Decision Making	2025-10-11	Show Accurate, scalable traffic monitoring is critical for real-time and long-term transportation management, particularly during disruptions such as natural disasters, large construction projects, or major policy changes like New York City's first-in-the-nation congestion pricing program. However, widespread sensor deployment remains limited due to high installation, maintenance, and data management costs. While traffic cameras offer a cost-effective alternative, existing video analytics struggle with dynamic camera viewpoints and massive data volumes from large camera networks. This study presents an end-to-end AI-based framework leveraging existing traffic camera infrastructure for high-resolution, longitudinal analysis at scale. A fine-tuned YOLOv11 model, trained on localized urban scenes, extracts multimodal traffic density and classification metrics in real time. To address inconsistencies from non-stationary pan-tilt-zoom cameras, we introduce a novel graph-based viewpoint normalization method. A domain-specific large language model was also integrated to process massive data from a 24/7 video stream to generate frequent, automated summaries of evolving traffic patterns, a task far exceeding manual capabilities. We validated the system using over 9 million images from roughly 1,000 traffic cameras during the early rollout of NYC congestion pricing in 2025. Results show a 9% decline in weekday passenger vehicle density within the Congestion Relief Zone, early truck volume reductions with signs of rebound, and consistent increases in pedestrian and cyclist activity at corridor and zonal scales. Experiments showed that example-based prompts improved LLM's numerical accuracy and reduced hallucinations. These findings demonstrate the framework's potential as a practical, infrastructure-ready solution for large-scale, policy-relevant traffic monitoring with minimal human intervention.		None
Modern Deep Learning Approaches for Cricket Shot Classification: A Comprehensive Baseline Study	2025-10-10	Show Cricket shot classification from video sequences remains a challenging problem in sports video analysis, requiring effective modeling of both spatial and temporal features. This paper presents the first comprehensive baseline study comparing seven different deep learning approaches across four distinct research paradigms for cricket shot classification. We implement and systematically evaluate traditional CNN-LSTM architectures, attention-based models, vision transformers, transfer learning approaches, and modern EfficientNet-GRU combinations on a unified benchmark. A critical finding of our study is the significant performance gap between claims in academic literature and practical implementation results. While previous papers reported accuracies of 96% (Balaji LRCN), 99.2% (IJERCSE), and 93% (Sensors), our standardized re-implementations achieve 46.0%, 55.6%, and 57.7% respectively. Our modern SOTA approach, combining EfficientNet-B0 with a GRU-based temporal model, achieves 92.25% accuracy, demonstrating that substantial improvements are possible with modern architectures and systematic optimization. All implementations follow modern MLOps practices with PyTorch Lightning, providing a reproducible research platform that exposes the critical importance of standardized evaluation protocols in sports video analysis research.		None
LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation	2025-10-09	Show Video diffusion models (DMs) have enabled high-quality video synthesis. However, their computation costs scale quadratically with sequence length because self-attention has quadratic complexity. While linear attention lowers the cost, fully replacing quadratic attention requires expensive pretraining due to the limited expressiveness of linear attention and the complexity of spatiotemporal modeling in video generation. In this paper, we present LinVideo, an efficient data-free post-training framework that replaces a target number of self-attention modules with linear attention while preserving the original model's performance. First, we observe a significant disparity in the replaceability of different layers. Instead of manual or heuristic choices, we frame layer selection as a binary classification problem and propose selective transfer, which automatically and progressively converts layers to linear attention with minimal performance impact. Additionally, to overcome the ineffectiveness and inefficiency of existing objectives for this transfer process, we introduce an anytime distribution matching (ADM) objective that aligns the distributions of samples across any timestep along the sampling trajectory. This objective is efficient and recovers model performance. Extensive experiments show that our method achieves a 1.25-2.00x speedup while preserving generation quality, and our 4-step distilled model further delivers a 15.92x latency reduction with minimal visual quality drop.	Code ... Code will be released upon acceptance	None
Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation	2025-10-09	Show Accurate and efficient Video Quality Assessment (VQA) has long been a key research challenge. Current mainstream VQA methods typically improve performance by pretraining on large-scale classification datasets (e.g., ImageNet, Kinetics-400), followed by fine-tuning on VQA datasets. However, this strategy presents two significant challenges: (1) merely transferring semantic knowledge learned from pretraining is insufficient for VQA, as video quality depends on multiple factors (e.g., semantics, distortion, motion, aesthetics); (2) pretraining on large-scale datasets demands enormous computational resources, often dozens or even hundreds of times greater than training directly on VQA datasets. Recently, Vision-Language Models (VLMs) have shown remarkable generalization capabilities across a wide range of visual tasks, and have begun to demonstrate promising potential in quality assessment. In this work, we propose Q-CLIP, the first fully VLMs-based framework for VQA. Q-CLIP enhances both visual and textual representations through a Shared Cross-Modal Adapter (SCMA), which contains only a minimal number of trainable parameters and is the only component that requires training. This design significantly reduces computational cost. In addition, we introduce a set of five learnable quality-level prompts to guide the VLMs in perceiving subtle quality variations, thereby further enhancing the model's sensitivity to video quality. Furthermore, we investigate the impact of different frame sampling strategies on VQA performance, and find that frame-difference-based sampling leads to better generalization performance across datasets. Extensive experiments demonstrate that Q-CLIP exhibits excellent performance on several VQA datasets.		None
TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba	2025-10-09	Show Transformer-based architectures have become the backbone of both uni-modal and multi-modal foundation models, largely due to their scalability via attention mechanisms, resulting in a rich ecosystem of publicly available pre-trained models such as LLaVA, CLIP, and DeiT, etc. In parallel, emerging sub-quadratic architectures like Mamba offer promising efficiency gains by enabling global context modeling with linear complexity. However, training these architectures from scratch remains resource-intensive (e.g., in terms of data and time). Motivated by this challenge, we explore a cross-architecture knowledge transfer paradigm, termed TransMamba, that facilitates the reuse of Transformer pre-trained knowledge. We propose a two-stage framework to accelerate the training of Mamba-based models, ensuring their effectiveness across both uni-modal and multi-modal tasks. The first stage leverages pre-trained Transformer models to initialize critical components of the Mamba architecture. To bridge architectural and dimensional gaps, we develop a selective weight subcloning strategy and a layered initialization scheme that prioritizes the early $n$ layers. Building on this initialization, the second stage introduces an adaptive multi-directional knowledge distillation method. This mechanism employs layer-wise adaptive scaling factors to align Mamba representations with their Transformer counterparts, while accommodating the scanning order variations inherent to multi-modal Mamba architectures. Despite operating with a reduced training dataset and a more compact model architecture, TransMamba consistently outperforms baseline approaches across diverse mamba-based backbones (e.g., PlainMamba, Vmamba, ViM and VideoMamba) and downstream tasks (e.g., image classification, visual question answering, text-video retrieval and multimodal reasoning). All code and implementation details will be released.		None
A Rotation-Invariant Embedded Platform for (Neural) Cellular Automata	2025-10-08	Show This paper presents a rotation-invariant embedded platform for simulating (neural) cellular automata (NCA) in modular robotic systems. Inspired by previous work on physical NCA, we introduce key innovations that overcome limitations in prior hardware designs. Our platform features a symmetric, modular structure, enabling seamless connections between cells regardless of orientation. Additionally, each cell is battery-powered, allowing it to operate independently and retain its state even when disconnected from the collective. To demonstrate the platform's applicability, we present a novel rotation-invariant NCA model for isotropic shape classification. The proposed system provides a robust foundation for exploring the physical realization of NCA, with potential applications in distributed robotic systems and self-organizing structures. Our implementation, including hardware, software code, a simulator, and a video, is openly shared at: https://github.com/dwoiwode/embedded_nca	Accep... Accepted for ALIFE 2025	Code Link
Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization	2025-10-08	Show Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation. A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios, which limits the generalization ability of conventional methods. We introduce Continual AQA (CAQA), which equips AQA with Continual Learning (CL) capabilities to handle evolving distributions while mitigating catastrophic forgetting. Although parameter-efficient fine-tuning of pretrained models has shown promise in CL for image classification, we find it insufficient for CAQA. Our empirical and theoretical analyses reveal two insights: (i) Full-Parameter Fine-Tuning (FPFT) is necessary for effective representation learning; yet (ii) uncontrolled FPFT induces overfitting and feature manifold shift, thereby aggravating forgetting. To address this, we propose Adaptive Manifold-Aligned Graph Regularization (MAGR++), which couples backbone fine-tuning that stabilizes shallow layers while adapting deeper ones with a two-step feature rectification pipeline: a manifold projector to translate deviated historical features into the current representation space, and a graph regularizer to align local and global distributions. We construct four CAQA benchmarks from three datasets with tailored evaluation protocols and strong baselines, enabling systematic cross-dataset comparison. Extensive experiments show that MAGR++ achieves state-of-the-art performance, with average correlation gains of 3.6% offline and 12.2% online over the strongest baseline, confirming its robustness and effectiveness. Our code is available at https://github.com/ZhouKanglei/MAGRPP.	Exten... Extended Version of MAGR (ECCV 2024 Oral Presentation)	Code Link
TFM Dataset: A Novel Multi-task Dataset and Integrated Pipeline for Automated Tear Film Break-Up Segmentation	2025-10-08	Show Tear film break-up (TFBU) analysis is critical for diagnosing dry eye syndrome, but automated TFBU segmentation remains challenging due to the lack of annotated datasets and integrated solutions. This paper introduces the Tear Film Multi-task (TFM) Dataset, the first comprehensive dataset for multi-task tear film analysis, comprising 15 high-resolution videos (totaling 6,247 frames) annotated with three vision tasks: frame-level classification ('clear', 'closed', 'broken', 'blur'), Placido Ring detection, and pixel-wise TFBU area segmentation. Leveraging this dataset, we first propose TF-Net, a novel and efficient baseline segmentation model. TF-Net incorporates a MobileOne-mini backbone with re-parameterization techniques and an enhanced feature pyramid network to achieve a favorable balance between accuracy and computational efficiency for real-time clinical applications. We further establish benchmark performance on the TFM segmentation subset by comparing TF-Net against several state-of-the-art medical image segmentation models. Furthermore, we design TF-Collab, a novel integrated real-time pipeline that synergistically leverages models trained on all three tasks of the TFM dataset. By sequentially orchestrating frame classification for BUT determination, pupil region localization for input standardization, and TFBU segmentation, TF-Collab fully automates the analysis. Experimental results demonstrate the effectiveness of the proposed TF-Net and TF-Collab, providing a foundation for future research in ocular surface diagnostics. Our code and the TFM datasets are available at https://github.com/glory-wan/TF-Net		Code Link
Enhancing Fitness Movement Recognition with Attention Mechanism and Pre-Trained Feature Extractors	2025-10-07	Show Fitness movement recognition, a focused subdomain of human activity recognition (HAR), plays a vital role in health monitoring, rehabilitation, and personalized fitness training by enabling automated exercise classification from video data. However, many existing deep learning approaches rely on computationally intensive 3D models, limiting their feasibility in real-time or resource-constrained settings. In this paper, we present a lightweight and effective framework that integrates pre-trained 2D Convolutional Neural Networks (CNNs) such as ResNet50, EfficientNet, and Vision Transformers (ViT) with a Long Short-Term Memory (LSTM) network enhanced by spatial attention. These models efficiently extract spatial features while the LSTM captures temporal dependencies, and the attention mechanism emphasizes informative segments. We evaluate the framework on a curated subset of the UCF101 dataset, achieving a peak accuracy of 93.34% with the ResNet50-based configuration. Comparative results demonstrate the superiority of our approach over several state-of-the-art HAR systems. The proposed method offers a scalable and real-time-capable solution for fitness activity recognition with broader applications in vision-based health and activity monitoring.	6 pag... 6 pages,9 figures, 2025 28th International Conference on Computer and Information Technology (ICCIT)	None
LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders	2025-10-07	Show In this work, we introduce long-video masked-embedding autoencoders (LV-MAE), a self-supervised learning framework for long video representation. Our approach treats short- and long-span dependencies as two separate tasks. Such decoupling allows for a more intuitive video processing where short-span spatiotemporal primitives are first encoded and are then used to capture long-range dependencies across consecutive video segments. To achieve this, we leverage advanced off-the-shelf multimodal encoders to extract representations from short segments within the long video, followed by pre-training a masked-embedding autoencoder capturing high-level interactions across segments. LV-MAE is highly efficient to train and enables the processing of much longer videos by alleviating the constraint on the number of input frames. Furthermore, unlike existing methods that typically pre-train on short-video datasets, our approach offers self-supervised pre-training using long video samples (e.g., 20+ minutes video clips) at scale. Using LV-MAE representations, we achieve state-of-the-art results on three long-video benchmarks -- LVU, COIN, and Breakfast -- employing only a simple classification head for either attentive or linear probing. Finally, to assess LV-MAE pre-training and visualize its reconstruction quality, we leverage the video-language aligned space of short video representations to monitor LV-MAE through video-text retrieval. Code is available at https://github.com/amazon-science/lv-mae.	Accep... Accepted to the International Conference on Computer Vision, ICCV 2025	Code Link
Can Video Large Multimodal Models Think Like Doubters-or Double-Down: A Study on Defeasible Video Entailment	2025-10-07	Show Video Large Multimodal Models (VLMMs) have made impressive strides in understanding video content, but they often struggle with abstract and adaptive reasoning-the ability to revise their interpretations when new information emerges. In reality, conclusions are rarely set in stone; additional context can strengthen or weaken an initial inference. To address this, we introduce Defeasible Video Entailment (DVidE), a new task that challenges models to think like doubters, constantly updating their reasoning based on evolving evidence. In DVidE, given a video premise and a textual hypothesis, models must determine whether a new update strengthens or weakens the hypothesis (classification version) or generate a coherent update that modifies the entailment relationship (generation version). For solving the classification task, we propose the Chain of Counterfactual Thought framework, utilizing counterfactual reasoning, ASR-enhanced video content, and rationale refinement to reduce inference bias. For the generation task, we develop a framework that combines ASR output with a Large Language Model (LLM) to produce coherent, contextually relevant updates aligned with the intended strengthener or weakener goals. Additionally, we introduce a novel benchmark dataset, with strengthener/weakener annotations and an LLM-based evaluation metric specifically designed for assessing generative performance. Experimental results demonstrate significant improvements, highlighting our proposed method in enhancing dynamic reasoning capabilities of VLMMs.		None
CLAd-VR: Cognitive Load-based Adaptive Training for Machining Tasks in Virtual Reality	2025-10-06	Show With the growing need to effectively support workforce upskilling in the manufacturing sector, virtual reality is gaining popularity as a scalable training solution. However, most current systems are designed as static, step-by-step tutorials and do not adapt to a learner's needs or cognitive load, which is a critical factor in learning and longterm retention. We address this limitation with CLAd-VR, an adaptive VR training system that integrates realtime EEG-based sensing to measure the learner's cognitive load and adapt instruction accordingly, specifically for domain-specific tasks in manufacturing. The system features a VR training module for a precision drilling task, designed with multimodal instructional elements including animations, text, and video. Our cognitive load sensing pipeline uses a wearable EEG device to capture the trainee's neural activity, which is processed through an LSTM model to classify their cognitive load as low, optimal, or high in real time. Based on these classifications, the system dynamically adjusts task difficulty and delivers adaptive guidance using voice guidance, visual cues, or ghost hand animations. This paper introduces CLAd-VR system's architecture, including the EEG sensing hardware, real-time inference model, and adaptive VR interface.		None
VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL	2025-10-06	Show With the rapid advancement of AI-generated videos, there is an urgent need for effective detection tools to mitigate societal risks such as misinformation and reputational harm. In addition to accurate classification, it is essential that detection models provide interpretable explanations to ensure transparency for regulators and end users. To address these challenges, we introduce VidGuard-R1, the first video authenticity detector that fine-tunes a multi-modal large language model (MLLM) using group relative policy optimization (GRPO). Our model delivers both highly accurate judgments and insightful reasoning. We curate a challenging dataset of 140k real and AI-generated videos produced by state-of-the-art generation models, carefully designing the generation process to maximize discrimination difficulty. We then fine-tune Qwen-VL using GRPO with two specialized reward models that target temporal artifacts and generation complexity. Extensive experiments demonstrate that VidGuard-R1 achieves state-of-the-art zero-shot performance on existing benchmarks, with additional training pushing accuracy above 95%. Case studies further show that VidGuard-R1 produces precise and interpretable rationales behind its predictions. The code is publicly available at https://VidGuard-R1.github.io.		None
Latent Uncertainty Representations for Video-based Driver Action and Intention Recognition	2025-10-06	Show Deep neural networks (DNNs) are increasingly applied to safety-critical tasks in resource-constrained environments, such as video-based driver action and intention recognition. While last layer probabilistic deep learning (LL-PDL) methods can detect out-of-distribution (OOD) instances, their performance varies. As an alternative to last layer approaches, we propose extending pre-trained DNNs with transformation layers to produce multiple latent representations to estimate the uncertainty. We evaluate our latent uncertainty representation (LUR) and repulsively trained LUR (RLUR) approaches against eight PDL methods across four video-based driver action and intention recognition datasets, comparing classification performance, calibration, and uncertainty-based OOD detection. We also contribute 28,000 frame-level action labels and 1,194 video-level intention labels for the NuScenes dataset. Our results show that LUR and RLUR achieve comparable in-distribution classification performance to other LL-PDL approaches. For uncertainty-based OOD detection, LUR matches top-performing PDL methods while being more efficient to train and easier to tune than approaches that require Markov-Chain Monte Carlo sampling or repulsive training procedures.	16 pa... 16 pages, 8 figures, 7 tables, under submission	None
Federated Learning for Surgical Vision in Appendicitis Classification: Results of the FedSurg EndoVis 2024 Challenge	2025-10-06	Show Purpose: The FedSurg challenge was designed to benchmark the state of the art in federated learning for surgical video classification. Its goal was to assess how well current methods generalize to unseen clinical centers and adapt through local fine-tuning while enabling collaborative model development without sharing patient data. Methods: Participants developed strategies to classify inflammation stages in appendicitis using a preliminary version of the multi-center Appendix300 video dataset. The challenge evaluated two tasks: generalization to an unseen center and center-specific adaptation after fine-tuning. Submitted approaches included foundation models with linear probing, metric learning with triplet loss, and various FL aggregation schemes (FedAvg, FedMedian, FedSAM). Performance was assessed using F1-score and Expected Cost, with ranking robustness evaluated via bootstrapping and statistical testing. Results: In the generalization task, performance across centers was limited. In the adaptation task, all teams improved after fine-tuning, though ranking stability was low. The ViViT-based submission achieved the strongest overall performance. The challenge highlighted limitations in generalization, sensitivity to class imbalance, and difficulties in hyperparameter tuning in decentralized training, while spatiotemporal modeling and context-aware preprocessing emerged as promising strategies. Conclusion: The FedSurg Challenge establishes the first benchmark for evaluating FL strategies in surgical video classification. Findings highlight the trade-off between local personalization and global robustness, and underscore the importance of architecture choice, preprocessing, and loss design. This benchmarking offers a reference point for future development of imbalance-aware, adaptive, and robust FL methods in clinical surgical AI.	A cha... A challenge report pre-print (31 pages), including 7 tables and 8 figures	None
Dual-Stage Reweighted MoE for Long-Tailed Egocentric Mistake Detection	2025-10-03	Show In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data. To handle the challenges posed by subtle and infrequent mistakes, we propose a Dual-Stage Reweighted Mixture-of-Experts (DR-MoE) framework. In the first stage, features are extracted using a frozen ViViT model and a LoRA-tuned ViViT model, which are combined through a feature-level expert module. In the second stage, three classifiers are trained with different objectives: reweighted cross-entropy to mitigate class imbalance, AUC loss to improve ranking under skewed distributions, and label-aware loss with sharpness-aware minimization to enhance calibration and generalization. Their predictions are fused using a classification-level expert module. The proposed method achieves strong performance, particularly in identifying rare and ambiguous mistake instances. The code is available at https://github.com/boyuh/DR-MoE.		Code Link
User to Video: A Model for Spammer Detection Inspired by Video Classification Technology	2025-10-02	Show This article is inspired by video classification technology. If the user behavior subspace is viewed as a frame image, consecutive frame images are viewed as a video. Following this novel idea, a model for spammer detection based on user videoization, called UVSD, is proposed. Firstly, a user2piexl algorithm for user pixelization is proposed. Considering the adversarial behavior of user stances, the user is viewed as a pixel, and the stance is quantified as the pixel's RGB. Secondly, a behavior2image algorithm is proposed for transforming user behavior subspace into frame images. Low-rank dense vectorization of subspace user relations is performed using representation learning, while cutting and diffusion algorithms are introduced to complete the frame imageization. Finally, user behavior videos are constructed based on temporal features. Subsequently, a video classification algorithm is combined to identify the spammers. Experiments using publicly available datasets, i.e., WEIBO and TWITTER, show an advantage of the UVSD model over state-of-the-art methods.	Accep... Accepted by International Joint Conference on Neural Networks (IJCNN) 2025	None
Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs	2025-10-01	Show Can humans identify AI-generated (fake) videos and provide grounded reasons? While video generation models have advanced rapidly, a critical dimension -- whether humans can detect deepfake traces within a generated video, i.e., spatiotemporal grounded visual artifacts that reveal a video as machine generated -- has been largely overlooked. We introduce DeeptraceReward, the first fine-grained, spatially- and temporally- aware benchmark that annotates human-perceived fake traces for video generation reward. The dataset comprises 4.3K detailed annotations across 3.3K high-quality generated videos. Each annotation provides a natural-language explanation, pinpoints a bounding-box region containing the perceived trace, and marks precise onset and offset timestamps. We consolidate these annotations into 9 major categories of deepfake traces that lead humans to identify a video as AI-generated, and train multimodal language models (LMs) as reward models to mimic human judgments and localizations. On DeeptraceReward, our 7B reward model outperforms GPT-5 by 34.7% on average across fake clue identification, grounding, and explanation. Interestingly, we observe a consistent difficulty gradient: binary fake v.s. real classification is substantially easier than fine-grained deepfake trace detection; within the latter, performance degrades from natural language explanations (easiest), to spatial grounding, to temporal labeling (hardest). By foregrounding human-perceived deepfake traces, DeeptraceReward provides a rigorous testbed and training signal for socially aware and trustworthy video generation.	Proje... Project Page: https://deeptracereward.github.io/	None
StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning	2025-09-30	Show Video Class-Incremental Learning (VCIL) seeks to develop models that continuously learn new action categories over time without forgetting previously acquired knowledge. Unlike traditional Class-Incremental Learning (CIL), VCIL introduces the added complexity of spatiotemporal structures, making it particularly challenging to mitigate catastrophic forgetting while effectively capturing both frame-shared semantics and temporal dynamics. Existing approaches either rely on exemplar rehearsal, raising concerns over memory and privacy, or adapt static image-based methods that neglect temporal modeling. To address these limitations, we propose Spatiotemporal Preservation and Routing (StPR), a unified and exemplar-free VCIL framework that explicitly disentangles and preserves spatiotemporal information. First, we introduce Frame-Shared Semantics Distillation (FSSD), which identifies semantically stable and meaningful channels by jointly considering semantic sensitivity and classification contribution. These important semantic channels are selectively regularized to maintain prior knowledge while allowing for adaptation. Second, we design a Temporal Decomposition-based Mixture-of-Experts (TD-MoE), which dynamically routes task-specific experts based on their temporal dynamics, enabling inference without task ID or stored exemplars. Together, StPR effectively leverages spatial semantics and temporal dynamics, achieving a unified, exemplar-free VCIL framework. Extensive experiments on UCF101, HMDB51, and Kinetics400 show that our method outperforms existing baselines while offering improved interpretability and efficiency in VCIL. Code is available in the supplementary materials.		None
Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions	2025-09-29	Show The evolution of digital communication systems and the designs of online platforms have inadvertently facilitated the subconscious propagation of toxic behavior. Giving rise to reactive responses to toxic behavior. Toxicity in online content and Artificial Intelligence Systems has become a serious challenge to individual and collective well-being around the world. It is more detrimental to society than we realize. Toxicity, expressed in language, image, and video, can be interpreted in various ways depending on the context of usage. Therefore, a comprehensive taxonomy is crucial to detect and mitigate toxicity in online content, Artificial Intelligence systems, and/or Large Language Models in a proactive manner. A comprehensive understanding of toxicity is likely to facilitate the design of practical solutions for toxicity detection and mitigation. The classification in published literature has focused on only a limited number of aspects of this very complex issue, with a pattern of reactive strategies in response to toxicity. This survey attempts to generate a comprehensive taxonomy of toxicity from various perspectives. It presents a holistic approach to explain the toxicity by understanding the context and environment that society is facing in the Artificial Intelligence era. This survey summarizes the toxicity-related datasets and research on toxicity detection and mitigation for Large Language Models, social media platforms, and other online platforms, detailing their attributes in textual mode, focused on the English language. Finally, we suggest the research gaps in toxicity mitigation based on datasets, mitigation strategies, Large Language Models, adaptability, explainability, and evaluation.		None
PET: Preference Evolution Tracking with LLM-Generated Explainable Distribution	2025-09-29	Show Understanding how user preference evolves over time is a fundamental challenge central to modern digital ecosystems, for which Large Language Models (LLMs) are an increasingly prominent and popular approach due to their ability to comprehend the rich semantic context within behavioral data. A common practice is to use LLMs to predict a user's next action by directly generating a ranked list of preferred items. Although effective for short-term prediction, the end-to-end generation paradigm inherently limits personalization. Its opaque decision-making process obscures holistic user profiling and exacerbates popularity bias. To address these limitations, we propose Preference Evolution Tracking (PET), a framework that reframes the task as inferring a dynamic probability distribution over a stable and interpretable lattice of preference clusters. By applying logit-probing and generative classification techniques, PET infers a user's preference as a probability distribution, enabling transparent preference learning. On public benchmarks (Yelp, MovieLens), PET improves ranking quality by up to 40% in NDCG over direct generation baselines. On a large-scale, real-world dataset from a short-video platform, it excels at ranking long-tail contents, significantly outperforming a SOTA production model by 7 times in the NDCG score. Ultimately, PET transforms the user profile model from direct preference list generation to a transparent distributional preference mapping, paving the way for more explainable, fair, and diverse personalization systems.		None
A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity	2025-09-29	Show Multimodal learning plays a pivotal role in advancing artificial intelligence systems by incorporating information from multiple modalities to build a more comprehensive representation. Despite its importance, current state-of-the-art models still suffer from severe limitations that prevent the successful development of a fully multimodal model. Such methods may not provide indicators that all the involved modalities are effectively aligned. As a result, some modalities may not be aligned, undermining the effectiveness of the model in downstream tasks where multiple modalities should provide additional information that the model fails to exploit. In this paper, we present TRIANGLE: TRI-modAl Neural Geometric LEarning, the novel proposed similarity measure that is directly computed in the higher-dimensional space spanned by the modality embeddings. TRIANGLE improves the joint alignment of three modalities via a triangle-area similarity, avoiding additional fusion layers or pairwise similarities. When incorporated in contrastive losses replacing cosine similarity, TRIANGLE significantly boosts the performance of multimodal modeling, while yielding interpretable alignment rationales. Extensive evaluation in three-modal tasks such as video-text and audio-text retrieval or audio-video classification, demonstrates that TRIANGLE achieves state-of-the-art results across different datasets improving the performance of cosine-based methods up to 9 points of Recall@1.	NeurIPS 2025	None
ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection	2025-09-27	Show Surgical triplet detection is a critical task in surgical video analysis. However, existing datasets like CholecT50 lack precise spatial bounding box annotations, rendering triplet classification at the image level insufficient for practical applications. The inclusion of bounding box annotations is essential to make this task meaningful, as they provide the spatial context necessary for accurate analysis and improved model generalizability. To address these shortcomings, we introduce ProstaTD, a large-scale, multi-institutional dataset for surgical triplet detection, developed from the technically demanding domain of robot-assisted prostatectomy. ProstaTD offers clinically defined temporal boundaries and high-precision bounding box annotations for each structured triplet activity. The dataset comprises 71,775 video frames and 196,490 annotated triplet instances, collected from 21 surgeries performed across multiple institutions, reflecting a broad range of surgical practices and intraoperative conditions. The annotation process was conducted under rigorous medical supervision and involved more than 60 contributors, including practicing surgeons and medically trained annotators, through multiple iterative phases of labeling and verification. To further facilitate future general-purpose surgical annotation, we developed two tailored labeling tools to improve efficiency and scalability in our annotation workflows. In addition, we created a surgical triplet detection evaluation toolkit that enables standardized and reproducible performance assessment across studies. ProstaTD is the largest and most diverse surgical triplet dataset to date, moving the field from simple classification to full detection with precise spatial and temporal boundaries and thereby providing a robust foundation for fair benchmarking.		None
EgoInstruct: An Egocentric Video Dataset of Face-to-face Instructional Interactions with Multi-modal LLM Benchmarking	2025-09-26	Show Analyzing instructional interactions between an instructor and a learner who are co-present in the same physical space is a critical problem for educational support and skill transfer. Yet such face-to-face instructional scenes have not been systematically studied in computer vision. We identify two key reasons: i) the lack of suitable datasets and ii) limited analytical techniques. To address this gap, we present a new egocentric video dataset of face-to-face instruction and provide ground-truth annotations for two fundamental tasks that serve as a first step toward a comprehensive understanding of instructional interactions: procedural step segmentation and conversation-state classification. Using this dataset, we benchmark multimodal large language models (MLLMs) against conventional task-specific models. Since face-to-face instruction involves multiple modalities (speech content and prosody, gaze and body motion, and visual context), effective understanding requires methods that handle verbal and nonverbal communication in an integrated manner. Accordingly, we evaluate recently introduced MLLMs that jointly process images, audio, and text. This evaluation quantifies the extent to which current machine learning models understand face-to-face instructional scenes. In experiments, MLLMs outperform specialized baselines even without task-specific fine-tuning, suggesting their promise for holistic understanding of instructional interactions.	Accep... Accepted to the I-HFM Workshop at ICCV 2025	None
Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2 Feature Representations for Video Action Analysis	2025-09-25	Show This study presents a comprehensive comparative analysis of two prominent self-supervised learning architectures for video action recognition: DINOv3, which processes frames independently through spatial feature extraction, and V-JEPA2, which employs joint temporal modeling across video sequences. We evaluate both approaches on the UCF Sports dataset, examining feature quality through multiple dimensions including classification accuracy, clustering performance, intra-class consistency, and inter-class discrimination. Our analysis reveals fundamental architectural trade-offs: DINOv3 achieves superior clustering performance (Silhouette score: 0.31 vs 0.21) and demonstrates exceptional discrimination capability (6.16x separation ratio) particularly for pose-identifiable actions, while V-JEPA2 exhibits consistent reliability across all action types with significantly lower performance variance (0.094 vs 0.288). Through action-specific evaluation, we identify that DINOv3's spatial processing architecture excels at static pose recognition but shows degraded performance on motion-dependent actions, whereas V-JEPA2's temporal modeling provides balanced representation quality across diverse action categories. These findings contribute to the understanding of architectural design choices in video analysis systems and provide empirical guidance for selecting appropriate feature extraction methods based on task requirements and reliability constraints.		None
Concepts in Motion: Temporal Bottlenecks for Interpretable Video Classification	2025-09-25	Show Conceptual models such as Concept Bottleneck Models (CBMs) have driven substantial progress in improving interpretability for image classification by leveraging human-interpretable concepts. However, extending these models from static images to sequences of images, such as video data, introduces a significant challenge due to the temporal dependencies inherent in videos, which are essential for capturing actions and events. In this work, we introduce MoTIF (Moving Temporal Interpretable Framework), an architectural design inspired by a transformer that adapts the concept bottleneck framework for video classification and handles sequences of arbitrary length. Within the video domain, concepts refer to semantic entities such as objects, attributes, or higher-level components (e.g., 'bow', 'mount', 'shoot') that reoccur across time - forming motifs collectively describing and explaining actions. Our design explicitly enables three complementary perspectives: global concept importance across the entire video, local concept relevance within specific windows, and temporal dependencies of a concept over time. Our results demonstrate that the concept-based modeling paradigm can be effectively transferred to video data, enabling a better understanding of concept contributions in temporal contexts while maintaining competitive performance. Code available at github.com/patrick-knab/MoTIF.		Code Link
Learning to Stop: Reinforcement Learning for Efficient Patient-Level Echocardiographic Classification	2025-09-24	Show Guidelines for transthoracic echocardiographic examination recommend the acquisition of multiple video clips from different views of the heart, resulting in a large number of clips. Typically, automated methods, for instance disease classifiers, either use one clip or average predictions from all clips. Relying on one clip ignores complementary information available from other clips, while using all clips is computationally expensive and may be prohibitive for clinical adoption. To select the optimal subset of clips that maximize performance for a specific task (image-based disease classification), we propose a method optimized through reinforcement learning. In our method, an agent learns to either keep processing view-specific clips to reduce the disease classification uncertainty, or stop processing if the achieved classification confidence is sufficient. Furthermore, we propose a learnable attention-based aggregation method as a flexible way of fusing information from multiple clips. The proposed method obtains an AUC of 0.91 on the task of detecting cardiac amyloidosis using only 30% of all clips, exceeding the performance achieved from using all clips and from other benchmarks.	publi... published in MICCAI-ASMUS 2025	None
Anatomically Constrained Transformers for Cardiac Amyloidosis Classification	2025-09-24	Show Cardiac amyloidosis (CA) is a rare cardiomyopathy, with typical abnormalities in clinical measurements from echocardiograms such as reduced global longitudinal strain of the myocardium. An alternative approach for detecting CA is via neural networks, using video classification models such as convolutional neural networks. These models process entire video clips, but provide no assurance that classification is based on clinically relevant features known to be associated with CA. An alternative paradigm for disease classification is to apply models to quantitative features such as strain, ensuring that the classification relates to clinically relevant features. Drawing inspiration from this approach, we explicitly constrain a transformer model to the anatomical region where many known CA abnormalities occur -- the myocardium, which we embed as a set of deforming points and corresponding sampled image patches into input tokens. We show that our anatomical constraint can also be applied to the popular self-supervised learning masked autoencoder pre-training, where we propose to mask and reconstruct only anatomical patches. We show that by constraining both the transformer and pre-training task to the myocardium where CA imaging features are localized, we achieve increased performance on a CA classification task compared to full video transformers. Our model provides an explicit guarantee that the classification is focused on only anatomical regions of the echo, and enables us to visualize transformer attention scores over the deforming myocardium.	Publi... Published in MICCAI - ASMUS 2025	None
Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening	2025-09-23	Show Our objective is to develop compact video representations that are sensitive to visual change over time. To measure such time-sensitivity, we introduce a new task: chiral action recognition, where one needs to distinguish between a pair of temporally opposite actions, such as "opening vs. closing a door", "approaching vs. moving away from something", "folding vs. unfolding paper", etc. Such actions (i) occur frequently in everyday life, (ii) require understanding of simple visual change over time (in object state, size, spatial position, count . . . ), and (iii) are known to be poorly represented by many video embeddings. Our goal is to build time aware video representations which offer linear separability between these chiral pairs. To that end, we propose a self-supervised adaptation recipe to inject time-sensitivity into a sequence of frozen image features. Our model is based on an auto-encoder with a latent space with inductive bias inspired by perceptual straightening. We show that this results in a compact but time-sensitive video representation for the proposed task across three datasets: Something-Something, EPIC-Kitchens, and Charade. Our method (i) outperforms much larger video models pre-trained on large-scale video datasets, and (ii) leads to an improvement in classification performance on standard benchmarks when combined with these existing models.	Proje... Project page: https://bpiyush.github.io/lift-website/	Code Link
Track-On2: Enhancing Online Point Tracking with Memory	2025-09-23	Show In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across video frames under significant appearance changes, motion, and occlusion. We target the online setting, i.e. tracking points frame-by-frame, making it suitable for real-time and streaming applications. We extend our prior model Track-On into Track-On2, a simple and efficient transformer-based model for online long-term tracking. Track-On2 improves both performance and efficiency through architectural refinements, more effective use of memory, and improved synthetic training strategies. Unlike prior approaches that rely on full-sequence access or iterative updates, our model processes frames causally and maintains temporal coherence via a memory mechanism, which is key to handling drift and occlusions without requiring future frames. At inference, we perform coarse patch-level classification followed by refinement. Beyond architecture, we systematically study synthetic training setups and their impact on memory behavior, showing how they shape temporal robustness over long sequences. Through comprehensive experiments, Track-On2 achieves state-of-the-art results across five synthetic and real-world benchmarks, surpassing prior online trackers and even strong offline methods that exploit bidirectional context. These results highlight the effectiveness of causal, memory-based architectures trained purely on synthetic data as scalable solutions for real-world point tracking. Project page: https://kuis-ai.github.io/track_on2		Code Link
Injecting Explainability and Lightweight Design into Weakly Supervised Video Anomaly Detection Systems	2025-09-23	Show Weakly Supervised Monitoring Anomaly Detection (WSMAD) utilizes weak supervision learning to identify anomalies, a critical task for smart city monitoring. However, existing multimodal approaches often fail to meet the real-time and interpretability requirements of edge devices due to their complexity. This paper presents TCVADS (Two-stage Cross-modal Video Anomaly Detection System), which leverages knowledge distillation and cross-modal contrastive learning to enable efficient, accurate, and interpretable anomaly detection on edge devices.TCVADS operates in two stages: coarse-grained rapid classification and fine-grained detailed analysis. In the first stage, TCVADS extracts features from video frames and inputs them into a time series analysis module, which acts as the teacher model. Insights are then transferred via knowledge distillation to a simplified convolutional network (student model) for binary classification. Upon detecting an anomaly, the second stage is triggered, employing a fine-grained multi-class classification model. This stage uses CLIP for cross-modal contrastive learning with text and images, enhancing interpretability and achieving refined classification through specially designed triplet textual relationships. Experimental results demonstrate that TCVADS significantly outperforms existing methods in model performance, detection efficiency, and interpretability, offering valuable contributions to smart city monitoring applications.		None
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging	2025-09-23	Show Foundation models update slowly due to resource-intensive training, whereas domain-specific models evolve rapidly between releases. Model merging seeks to combine multiple expert models into a single, more capable model, reducing storage and serving costs while supporting decentralized development. Despite its potential, previous studies have primarily focused on merging visual classification models or Large Language Models (LLMs) for code and math tasks. Recently, Multimodal LLMs (MLLMs) that extend LLMs through large-scale multimodal training have gained traction. However, there lacks a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation. In this paper, $\textbf{(i)}$ we introduce a model merging benchmark for MLLMs, which includes multiple tasks such as VQA, Geometry, Chart, OCR, and Grounding, studying both LoRA and full fine-tuning models. Moreover, we explore how model merging can combine different modalities (e.g., vision-language, audio-language, and video-language models), moving toward the Omni-language model. $\textbf{(ii)}$ We implement 10 model merging algorithms on the benchmark. Furthermore, we propose a novel method that removes noise from task vectors and robustly optimizes the merged vector based on a loss defined over task vector interactions, achieving an average performance gain of 2.48%. $\textbf{(iii)}$ We find that model merging offers a promising way for building improved MLLMs without requiring training data. Our results also demonstrate that the complementarity among multiple modalities outperforms individual modalities.		None
Fine-Tuning Robot Policies While Maintaining User Privacy	2025-09-22	Show Recent works introduce general-purpose robot policies. These policies provide a strong prior over how robots should behave -- e.g., how a robot arm should manipulate food items. But in order for robots to match an individual person's needs, users typically fine-tune these generalized policies -- e.g., showing the robot arm how to make their own preferred dinners. Importantly, during the process of personalizing robots, end-users leak data about their preferences, habits, and styles (e.g., the foods they prefer to eat). Other agents can simply roll-out the fine-tuned policy and see these personally-trained behaviors. This leads to a fundamental challenge: how can we develop robots that personalize actions while keeping learning private from external agents? We here explore this emerging topic in human-robot interaction and develop PRoP, a model-agnostic framework for personalized and private robot policies. Our core idea is to equip each user with a unique key; this key is then used to mathematically transform the weights of the robot's network. With the correct key, the robot's policy switches to match that user's preferences -- but with incorrect keys, the robot reverts to its baseline behaviors. We show the general applicability of our method across multiple model types in imitation learning, reinforcement learning, and classification tasks. PRoP is practically advantageous because it retains the architecture and behaviors of the original policy, and experimentally outperforms existing encoder-based approaches. See videos and code here: https://prop-icra26.github.io.		None
Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model	2025-09-19	Show Group activity detection (GAD) aims to simultaneously identify group members and categorize their collective activities within video sequences. Existing deep learning-based methods develop specialized architectures (e.g., transformer networks) to model the dynamics of individual roles and semantic dependencies between individuals and groups. However, they rely solely on implicit pattern recognition from visual features and struggle with contextual reasoning and explainability. In this work, we propose LIR-GAD, a novel framework of language-instructed reasoning for GAD via Multimodal Large Language Model (MLLM). Our approach expand the original vocabulary of MLLM by introducing an activity-level token and multiple cluster-specific tokens. We process video frames alongside two specially designed tokens and language instructions, which are then integrated into the MLLM. The pretrained commonsense knowledge embedded in the MLLM enables the token and tokens to effectively capture the semantic information of collective activities and learn distinct representational features of different groups, respectively. Also, we introduce a multi-label classification loss to further enhance the token's ability to learn discriminative semantic representations. Then, we design a Multimodal Dual-Alignment Fusion (MDAF) module that integrates MLLM's hidden embeddings corresponding to the designed tokens with visual features, significantly enhancing the performance of GAD. Both quantitative and qualitative experiments demonstrate the superior performance of our proposed method in GAD taks.	9 pages, 5 figures	None
Improving Autism Detection with Multimodal Behavioral Analysis	2025-09-19	Show Due to the complex and resource-intensive nature of diagnosing Autism Spectrum Condition (ASC), several computer-aided diagnostic support methods have been proposed to detect autism by analyzing behavioral cues in patient video data. While these models show promising results on some datasets, they struggle with poor gaze feature performance and lack of real-world generalizability. To tackle these challenges, we analyze a standardized video dataset comprising 168 participants with ASC (46% female) and 157 non-autistic participants (46% female), making it, to our knowledge, the largest and most balanced dataset available. We conduct a multimodal analysis of facial expressions, voice prosody, head motion, heart rate variability (HRV), and gaze behavior. To address the limitations of prior gaze models, we introduce novel statistical descriptors that quantify variability in eye gaze angles, improving gaze-based classification accuracy from 64% to 69% and aligning computational findings with clinical research on gaze aversion in ASC. Using late fusion, we achieve a classification accuracy of 74%, demonstrating the effectiveness of integrating behavioral markers across multiple modalities. Our findings highlight the potential for scalable, video-based screening tools to support autism assessment.		None
AToken: A Unified Tokenizer for Vision	2025-09-19	Show We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or understanding for single modalities, AToken encodes these diverse visual inputs into a shared 4D latent space, unifying both tasks and modalities in a single framework. Specifically, we introduce a pure transformer architecture with 4D rotary position embeddings to process visual inputs of arbitrary resolutions and temporal durations. To ensure stable training, we introduce an adversarial-free training objective that combines perceptual and Gram matrix losses, achieving state-of-the-art reconstruction quality. By employing a progressive training curriculum, AToken gradually expands from single images, videos, and 3D, and supports both continuous and discrete latent tokens. AToken achieves 0.21 rFID with 82.2% ImageNet accuracy for images, 3.01 rFVD with 40.2% MSRVTT retrieval for videos, and 28.28 PSNR with 90.9% classification accuracy for 3D.. In downstream applications, AToken enables both visual generation tasks (e.g., image generation with continuous and discrete tokens, text-to-video generation, image-to-3D synthesis) and understanding tasks (e.g., multimodal LLMs), achieving competitive performance across all benchmarks. These results shed light on the next-generation multimodal AI systems built upon unified visual tokenization.	30 pages, 14 figures	None
V-SenseDrive: A Privacy-Preserving Road Video and In-Vehicle Sensor Fusion Framework for Road Safety & Driver Behaviour Modelling	2025-09-18	Show Road traffic accidents remain a major public health challenge, particularly in countries with heterogeneous road conditions, mixed traffic flow, and variable driving discipline, such as Pakistan. Reliable detection of unsafe driving behaviours is a prerequisite for improving road safety, enabling advanced driver assistance systems (ADAS), and supporting data driven decisions in insurance and fleet management. Most of existing datasets originate from the developed countries with limited representation of the behavioural diversity observed in emerging economies and the driver's face recording voilates the privacy preservation. We present V-SenseDrive, the first privacy-preserving multimodal driver behaviour dataset collected entirely within the Pakistani driving environment. V-SenseDrive combines smartphone based inertial and GPS sensor data with synchronized road facing video to record three target driving behaviours (normal, aggressive, and risky) on multiple types of roads, including urban arterials, secondary roads, and motorways. Data was gathered using a custom Android application designed to capture high frequency accelerometer, gyroscope, and GPS streams alongside continuous video, with all sources precisely time aligned to enable multimodal analysis. The focus of this work is on the data acquisition process, covering participant selection, driving scenarios, environmental considerations, and sensor video synchronization techniques. The dataset is structured into raw, processed, and semantic layers, ensuring adaptability for future research in driver behaviour classification, traffic safety analysis, and ADAS development. By representing real world driving in Pakistan, V-SenseDrive fills a critical gap in the global landscape of driver behaviour datasets and lays the groundwork for context aware intelligent transportation solutions.		None
Temporally Heterogeneous Graph Contrastive Learning for Multimodal Acoustic event Classification	2025-09-18	Show Multimodal acoustic event classification plays a key role in audio-visual systems. Although combining audio and visual signals improves recognition, it is still difficult to align them over time and to reduce the effect of noise across modalities. Existing methods often treat audio and visual streams separately, fusing features later with contrastive or mutual information objectives. Recent advances explore multimodal graph learning, but most fail to distinguish between intra- and inter-modal temporal dependencies. To address this, we propose Temporally Heterogeneous Graph-based Contrastive Learning (THGCL). Our framework constructs a temporal graph for each event, where audio and video segments form nodes and their temporal links form edges. We introduce Gaussian processes for intra-modal smoothness, Hawkes processes for inter-modal decay, and contrastive learning to capture fine-grained relationships. Experiments on AudioSet show that THGCL achieves state-of-the-art performance.		None
Music4All A+A: A Multimodal Dataset for Music Information Retrieval Tasks	2025-09-18	Show Music is characterized by aspects related to different modalities, such as the audio signal, the lyrics, or the music video clips. This has motivated the development of multimodal datasets and methods for Music Information Retrieval (MIR) tasks such as genre classification or autotagging. Music can be described at different levels of granularity, for instance defining genres at the level of artists or music albums. However, most datasets for multimodal MIR neglect this aspect and provide data at the level of individual music tracks. We aim to fill this gap by providing Music4All Artist and Album (Music4All A+A), a dataset for multimodal MIR tasks based on music artists and albums. Music4All A+A is built on top of the Music4All-Onion dataset, an existing track-level dataset for MIR tasks. Music4All A+A provides metadata, genre labels, image representations, and textual descriptors for 6,741 artists and 19,511 albums. Furthermore, since Music4All A+A is built on top of Music4All-Onion, it allows access to other multimodal data at the track level, including user--item interaction data. This renders Music4All A+A suitable for a broad range of MIR tasks, including multimodal music recommendation, at several levels of granularity. To showcase the use of Music4All A+A, we carry out experiments on multimodal genre classification of artists and albums, including an analysis in missing-modality scenarios, and a quantitative comparison with genre classification in the movie domain. Our experiments show that images are more informative for classifying the genres of artists and albums, and that several multimodal models for genre classification struggle in generalizing across domains. We provide the code to reproduce our experiments at https://github.com/hcai-mms/Music4All-A-A, the dataset is linked in the repository and provided open-source under a CC BY-NC-SA 4.0 license.	7 pag... 7 pages, 6 tables, IEEE International Conference on Content-Based Multimedia Indexing (IEEE CBMI)	Code Link
Pre-training Autoencoder for Acoustic Event Classification via Blinky	2025-09-18	Show In the acoustic event classification (AEC) framework that employs Blinkies, audio signals are converted into LED light emissions and subsequently captured by a single video camera. However, the 30 fps optical transmission channel conveys only about 0.2% of the normal audio bandwidth and is highly susceptible to noise. We propose a novel sound-to-light conversion method that leverages the encoder of a pre-trained autoencoder (AE) to distill compact, discriminative features from the recorded audio. To pre-train the AE, we adopt a noise-robust learning strategy in which artificial noise is injected into the encoder's latent representations during training, thereby enhancing the model's robustness against channel noise. The encoder architecture is specifically designed for the memory footprint of contemporary edge devices such as the Raspberry Pi 4. In a simulation experiment on the ESC-50 dataset under a stringent 15 Hz bandwidth constraint, the proposed method achieved higher macro-F1 scores than conventional sound-to-light conversion approaches.	Accep... Accepted to APSIPA ASC 2025. 6 pages, 1 figures	None
BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports	2025-09-18	Show Badminton, known for having the fastest ball speeds among all sports, presents significant challenges to the field of computer vision, including player identification, court line detection, shuttlecock trajectory tracking, and player stroke-type classification. In this paper, we introduce a novel video clipping strategy to extract frames of each player's racket swing in a badminton broadcast match. These clipped frames are then processed by three existing models: one for Human Pose Estimation to obtain human skeletal joints, another for shuttlecock trajectory tracking, and the other for court line detection to determine player positions on the court. Leveraging these data as inputs, we propose Badminton Stroke-type Transformer (BST) to classify player stroke-types in singles. To the best of our knowledge, experimental results demonstrate that our method outperforms the previous state-of-the-art on the largest publicly available badminton video dataset (ShuttleSet), another badminton dataset (BadmintonDB), and a tennis dataset (TenniSet). These results suggest that effectively leveraging ball trajectory is a promising direction for action recognition in racket sports.	8 pag... 8 pages main paper, 2 pages references, 8 pages supplementary material	None
CrowdAgent: Multi-Agent Managed Multi-Source Annotation System	2025-09-17	Show High-quality annotated data is a cornerstone of modern Natural Language Processing (NLP). While recent methods begin to leverage diverse annotation sources-including Large Language Models (LLMs), Small Language Models (SLMs), and human experts-they often focus narrowly on the labeling step itself. A critical gap remains in the holistic process control required to manage these sources dynamically, addressing complex scheduling and quality-cost trade-offs in a unified manner. Inspired by real-world crowdsourcing companies, we introduce CrowdAgent, a multi-agent system that provides end-to-end process control by integrating task assignment, data annotation, and quality/cost management. It implements a novel methodology that rationally assigns tasks, enabling LLMs, SLMs, and human experts to advance synergistically in a collaborative annotation workflow. We demonstrate the effectiveness of CrowdAgent through extensive experiments on six diverse multimodal classification tasks. The source code and video demo are available at https://github.com/QMMMS/CrowdAgent.		Code Link
Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics	2025-09-17	Show Natural language is often the easiest and most convenient modality for humans to specify tasks for robots. However, learning to ground language to behavior typically requires impractical amounts of diverse, language-annotated demonstrations collected on each target robot. In this work, we aim to separate the problem of what to accomplish from how to accomplish it, as the former can benefit from substantial amounts of external observation-only data, and only the latter depends on a specific robot embodiment. To this end, we propose Video-Language Critic, a reward model that can be trained on readily available cross-embodiment data using contrastive learning and a temporal ranking objective, and use it to score behavior traces from a separate actor. When trained on Open X-Embodiment data, our reward model enables 2x more sample-efficient policy training on Meta-World tasks than a sparse reward only, despite a significant domain gap. Using in-domain data but in a challenging task generalization setting on Meta-World, we further demonstrate more sample-efficient training than is possible with prior language-conditioned reward models that are either trained with binary classification, use static images, or do not leverage the temporal information present in video data.	14 pa... 14 pages in the main text, 22 pages including references and supplementary materials. 3 figures and 3 tables in the main text, 6 figures and 3 tables in supplementary materials	None
Direct Video-Based Spatiotemporal Deep Learning for Cattle Lameness Detection	2025-09-17	Show Cattle lameness is a prevalent health problem in livestock farming, often resulting from hoof injuries or infections, and severely impacts animal welfare and productivity. Early and accurate detection is critical for minimizing economic losses and ensuring proper treatment. This study proposes a spatiotemporal deep learning framework for automated cattle lameness detection using publicly available video data. We curate and publicly release a balanced set of 50 online video clips featuring 42 individual cattle, recorded from multiple viewpoints in both indoor and outdoor environments. The videos were categorized into lame and non-lame classes based on visual gait characteristics and metadata descriptions. After applying data augmentation techniques to enhance generalization, two deep learning architectures were trained and evaluated: 3D Convolutional Neural Networks (3D CNN) and Convolutional Long-Short-Term Memory (ConvLSTM2D). The 3D CNN achieved a video-level classification accuracy of 90%, with a precision, recall, and F1 score of 90.9% each, outperforming the ConvLSTM2D model, which achieved 85% accuracy. Unlike conventional approaches that rely on multistage pipelines involving object detection and pose estimation, this study demonstrates the effectiveness of a direct end-to-end video classification approach. Compared with the best end-to-end prior method (C3D-ConvLSTM, 90.3%), our model achieves comparable accuracy while eliminating pose estimation pre-processing.The results indicate that deep learning models can successfully extract and learn spatio-temporal features from various video sources, enabling scalable and efficient cattle lameness detection in real-world farm settings.		None
Vi-SAFE: A Spatial-Temporal Framework for Efficient Violence Detection in Public Surveillance	2025-09-16	Show Violence detection in public surveillance is critical for public safety. This study addresses challenges such as small-scale targets, complex environments, and real-time temporal analysis. We propose Vi-SAFE, a spatial-temporal framework that integrates an enhanced YOLOv8 with a Temporal Segment Network (TSN) for video surveillance. The YOLOv8 model is optimized with GhostNetV3 as a lightweight backbone, an exponential moving average (EMA) attention mechanism, and pruning to reduce computational cost while maintaining accuracy. YOLOv8 and TSN are trained separately on pedestrian and violence datasets, where YOLOv8 extracts human regions and TSN performs binary classification of violent behavior. Experiments on the RWF-2000 dataset show that Vi-SAFE achieves an accuracy of 0.88, surpassing TSN alone (0.77) and outperforming existing methods in both accuracy and efficiency, demonstrating its effectiveness for public safety surveillance. Code is available at https://anonymous.4open.science/r/Vi-SAFE-3B42/README.md.		None
Compressed Video Quality Enhancement: Classifying and Benchmarking over Standards	2025-09-16	Show Compressed video quality enhancement (CVQE) is crucial for improving user experience with lossy video codecs like H.264/AVC, H.265/HEVC, and H.266/VVC. While deep learning based CVQE has driven significant progress, existing surveys still suffer from limitations: lack of systematic classification linking methods to specific standards and artifacts, insufficient comparative analysis of architectural paradigms across coding types, and underdeveloped benchmarking practices. To address these gaps, this paper presents three key contributions. First, it introduces a novel taxonomy classifying CVQE methods across architectural paradigms, coding standards, and compressed-domain feature utilization. Second, it proposes a unified benchmarking framework integrating modern compression protocols and standard test sequences for fair multi-criteria evaluation. Third, it provides a systematic analysis of the critical trade-offs between reconstruction performance and computational complexity observed in state-of-the-art methods and highlighting promising directions for future research. This comprehensive review aims to establish a foundation for consistent assessment and informed model selection in CVQE research and deployment.		None
Multimodal Hate Detection Using Dual-Stream Graph Neural Networks	2025-09-16	Show Hateful videos present serious risks to online safety and real-world well-being, necessitating effective detection methods. Although multimodal classification approaches integrating information from several modalities outperform unimodal ones, they typically neglect that even minimal hateful content defines a video's category. Specifically, they generally treat all content uniformly, instead of emphasizing the hateful components. Additionally, existing multimodal methods cannot systematically capture structured information in videos, limiting the effectiveness of multimodal fusion. To address these limitations, we propose a novel multimodal dual-stream graph neural network model. It constructs an instance graph by separating the given video into several instances to extract instance-level features. Then, a complementary weight graph assigns importance weights to these features, highlighting hateful instances. Importance weights and instance features are combined to generate video labels. Our model employs a graph-based framework to systematically model structured relationships within and across modalities. Extensive experiments on public datasets show that our model is state-of-the-art in hateful video classification and has strong explainability. Code is available: https://github.com/Multimodal-Intelligence-Lab-MIL/MultiHateGNN.		Code Link
Open-ended Hierarchical Streaming Video Understanding with Vision Language Models	2025-09-15	Show We introduce Hierarchical Streaming Video Understanding, a task that combines online temporal action localization with free-form description generation. Given the scarcity of datasets with hierarchical and fine-grained temporal annotations, we demonstrate that LLMs can effectively group atomic actions into higher-level events, enriching existing datasets. We then propose OpenHOUSE (Open-ended Hierarchical Online Understanding System for Events), which extends streaming action perception beyond action classification. OpenHOUSE features a specialized streaming module that accurately detects boundaries between closely adjacent actions, nearly doubling the performance of direct extensions of existing methods. We envision the future of streaming action perception in the integration of powerful generative models, with OpenHOUSE representing a key step in that direction.	17 pages	None
Organoid Tracker: A SAM2-Powered Platform for Zero-shot Cyst Analysis in Human Kidney Organoid Videos	2025-09-14	Show Recent advances in organoid models have revolutionized the study of human kidney disease mechanisms and drug discovery by enabling scalable, cost-effective research without the need for animal sacrifice. Here, we present a kidney organoid platform optimized for efficient screening in polycystic kidney disease (PKD). While these systems generate rich spatial-temporal microscopy video datasets, current manual approaches to analysis remain limited to coarse classifications (e.g., hit vs. non-hit), often missing valuable pixel-level and longitudinal information. To help overcome this bottleneck, we developed Organoid Tracker, a graphical user interface (GUI) platform designed with a modular plugin architecture, which empowers researchers to extract detailed, quantitative metrics without programming expertise. Built on the cutting-edge vision foundation model Segment Anything Model 2 (SAM2), Organoid Tracker enables zero-shot segmentation and automated analysis of spatial-temporal microscopy videos. It quantifies key metrics such as cyst formation rate, growth velocity, and morphological changes, while generating comprehensive reports. By providing an extensible, open-source framework, Organoid Tracker offers a powerful solution for improving and accelerating research in kidney development, PKD modeling, and therapeutic discovery. The platform is publicly available as open-source software at https://github.com/hrlblab/OrganoidTracker.		Code Link
D-CAT: Decoupled Cross-Attention Transfer between Sensor Modalities for Unimodal Inference	2025-09-11	Show Cross-modal transfer learning is used to improve multi-modal classification models (e.g., for human activity recognition in human-robot collaboration). However, existing methods require paired sensor data at both training and inference, limiting deployment in resource-constrained environments where full sensor suites are not economically and technically usable. To address this, we propose Decoupled Cross-Attention Transfer (D-CAT), a framework that aligns modality-specific representations without requiring joint sensor modality during inference. Our approach combines a self-attention module for feature extraction with a novel cross-attention alignment loss, which enforces the alignment of sensors' feature spaces without requiring the coupling of the classification pipelines of both modalities. We evaluate D-CAT on three multi-modal human activity datasets (IMU, video, and audio) under both in-distribution and out-of-distribution scenarios, comparing against uni-modal models. Results show that in in-distribution scenarios, transferring from high-performing modalities (e.g., video to IMU) yields up to 10% F1-score gains over uni-modal training. In out-of-distribution scenarios, even weaker source modalities (e.g., IMU to video) improve target performance, as long as the target model isn't overfitted on the training data. By enabling single-sensor inference with cross-modal knowledge, D-CAT reduces hardware redundancy for perception systems while maintaining accuracy, which is critical for cost-sensitive or adaptive deployments (e.g., assistive robots in homes with variable sensor availability). Code is available at https://github.com/Schindler-EPFL-Lab/D-CAT.		Code Link
Images in Motion?: A First Look into Video Leakage in Collaborative Deep Learning	2025-09-11	Show Federated learning (FL) allows multiple entities to train a shared model collaboratively. Its core, privacy-preserving principle is that participants only exchange model updates, such as gradients, and never their raw, sensitive data. This approach is fundamental for applications in domains where privacy and confidentiality are important. However, the security of this very mechanism is threatened by gradient inversion attacks, which can reverse-engineer private training data directly from the shared gradients, defeating the purpose of FL. While the impact of these attacks is known for image, text, and tabular data, their effect on video data remains an unexamined area of research. This paper presents the first analysis of video data leakage in FL using gradient inversion attacks. We evaluate two common video classification approaches: one employing pre-trained feature extractors and another that processes raw video frames with simple transformations. Our initial results indicate that the use of feature extractors offers greater resilience against gradient inversion attacks. We also demonstrate that image super-resolution techniques can enhance the frames extracted through gradient inversion attacks, enabling attackers to reconstruct higher-quality videos. Our experiments validate this across scenarios where the attacker has access to zero, one, or more reference frames from the target environment. We find that although feature extractors make attacks more challenging, leakage is still possible if the classifier lacks sufficient complexity. We, therefore, conclude that video data leakage in FL is a viable threat, and the conditions under which it occurs warrant further investigation.		None
Two Stage Context Learning with Large Language Models for Multimodal Stance Detection on Climate Change	2025-09-09	Show With the rapid proliferation of information across digital platforms, stance detection has emerged as a pivotal challenge in social media analysis. While most of the existing approaches focus solely on textual data, real-world social media content increasingly combines text with visual elements creating a need for advanced multimodal methods. To address this gap, we propose a multimodal stance detection framework that integrates textual and visual information through a hierarchical fusion approach. Our method first employs a Large Language Model to retrieve stance-relevant summaries from source text, while a domain-aware image caption generator interprets visual content in the context of the target topic. These modalities are then jointly modeled along with the reply text, through a specialized transformer module that captures interactions between the texts and images. The proposed modality fusion framework integrates diverse modalities to facilitate robust stance classification. We evaluate our approach on the MultiClimate dataset, a benchmark for climate change-related stance detection containing aligned video frames and transcripts. We achieve accuracy of 76.2%, precision of 76.3%, recall of 76.2% and F1-score of 76.2%, respectively, outperforming existing state-of-the-art approaches.		None
EHWGesture -- A dataset for multimodal understanding of clinical gestures	2025-09-09	Show Hand gesture understanding is essential for several applications in human-computer interaction, including automatic clinical assessment of hand dexterity. While deep learning has advanced static gesture recognition, dynamic gesture understanding remains challenging due to complex spatiotemporal variations. Moreover, existing datasets often lack multimodal and multi-view diversity, precise ground-truth tracking, and an action quality component embedded within gestures. This paper introduces EHWGesture, a multimodal video dataset for gesture understanding featuring five clinically relevant gestures. It includes over 1,100 recordings (6 hours), captured from 25 healthy subjects using two high-resolution RGB-Depth cameras and an event camera. A motion capture system provides precise ground-truth hand landmark tracking, and all devices are spatially calibrated and synchronized to ensure cross-modal alignment. Moreover, to embed an action quality task within gesture understanding, collected recordings are organized in classes of execution speed that mirror clinical evaluations of hand dexterity. Baseline experiments highlight the dataset's potential for gesture classification, gesture trigger detection, and action quality assessment. Thus, EHWGesture can serve as a comprehensive benchmark for advancing multimodal clinical gesture understanding.	Accep... Accepted at ICCV 2025 Workshop on AI-driven Skilled Activity Understanding, Assessment & Feedback Generation	None
Backdoor Attacks and Defenses in Computer Vision Domain: A Survey	2025-09-09	Show Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly growing literature on backdoor attacks and defenses in the computer-vision domain. We introduce a multi-dimensional taxonomy that organizes attacks and defenses by injection stage (dataset poisoning, model/parameter modification, inference-time injection), trigger type (patch, blended/frequency, semantic, transformation), labeling strategy (dirty-label vs. clean-label / feature-collision), representation stage (instance-specific, manifold/class-level, neuron/parameter hijacking, distributed encodings), and target task (classification, detection, segmentation, video, multimodal). For each axis we summarize representative methods, highlight evaluation practices, and discuss where defenses succeed or fail. For example, many classical sanitization and reverse-engineering tools are effective against reusable patch attacks but struggle with input-aware, sample-specific, or parameter-space backdoors and with transfer via compromised pre-trained encoders or hardware bit-flips. We synthesize trends, identify persistent gaps (supply-chain and hardware threats, certifiable defenses, cross-task benchmarks), and propose practical guidelines for threat-aware evaluation and layered defenses. This survey aims to orient researchers and practitioners to the current threat landscape and pressing research directions in secure computer vision.		None
Pothole Detection and Recognition based on Transfer Learning	2025-09-08	Show With the rapid development of computer vision and machine learning, automated methods for pothole detection and recognition based on image and video data have received significant attention. It is of great significance for social development to conduct an in-depth analysis of road images through feature extraction, thereby achieving automatic identification of the pothole condition in new images. Consequently, this is the main issue addressed in this study. Based on preprocessing techniques such as standardization, normalization, and data augmentation applied to the collected raw dataset, we continuously improved the network model based on experimental results. Ultimately, we constructed a deep learning feature extraction network ResNet50-EfficientNet-RegNet model based on transfer learning. This model exhibits high classification accuracy and computational efficiency. In terms of model evaluation, this study employed a comparative evaluation approach by comparing the performance of the proposed transfer learning model with other models, including Random Forest, MLP, SVM, and LightGBM. The comparison analysis was conducted based on metrics such as Accuracy, Recall, Precision, F1-score, and FPS, to assess the classification performance of the transfer learning model proposed in this paper. The results demonstrate that our model exhibits high performance in terms of recognition speed and accuracy, surpassing the performance of other models. Through careful parameter selection and model optimization, our transfer learning model achieved a classification accuracy of 97.78% (88/90) on the initial set of 90 test samples and 98.89% (890/900) on the expanded test set.		None
Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos	2025-09-08	Show In this study, we address the multimodal task of stereo sound event localization and detection with source distance estimation (3D SELD) in regular video content. 3D SELD is a complex task that combines temporal event classification with spatial localization, requiring reasoning across spatial, temporal, and semantic dimensions. The last is arguably the most challenging to model. Traditional SELD approaches typically rely on multichannel input, limiting their capacity to benefit from large-scale pre-training due to data constraints. To overcome this, we enhance a standard SELD architecture with semantic information by integrating pre-trained, contrastive language-aligned models: CLAP for audio and OWL-ViT for visual inputs. These embeddings are incorporated into a modified Conformer module tailored for multimodal fusion, which we refer to as the Cross-Modal Conformer. We perform an ablation study on the development set of the DCASE2025 Task3 Stereo SELD Dataset to assess the individual contributions of the language-aligned models and benchmark against the DCASE Task 3 baseline systems. Additionally, we detail the curation process of large synthetic audio and audio-visual datasets used for model pre-training. These datasets were further expanded through left-right channel swapping augmentation. Our approach, combining extensive pre-training, model ensembling, and visual post-processing, achieved second rank in the DCASE 2025 Challenge Task 3 (Track B), underscoring the effectiveness of our method. Future work will explore the modality-specific contributions and architectural refinements.	arXiv... arXiv admin note: substantial text overlap with arXiv:2507.04845	None
A New Dataset and Benchmark for Grounding Multimodal Misinformation	2025-09-08	Show The proliferation of online misinformation videos poses serious societal risks. Current datasets and detection methods primarily target binary classification or single-modality localization based on post-processed data, lacking the interpretability needed to counter persuasive misinformation. In this paper, we introduce the task of Grounding Multimodal Misinformation (GroundMM), which verifies multimodal content and localizes misleading segments across modalities. We present the first real-world dataset for this task, GroundLie360, featuring a taxonomy of misinformation types, fine-grained annotations across text, speech, and visuals, and validation with Snopes evidence and annotator reasoning. We also propose a VLM-based, QA-driven baseline, FakeMark, using single- and cross-modal cues for effective detection and grounding. Our experiments highlight the challenges of this task and lay a foundation for explainable multimodal misinformation detection.	6 pag... 6 pages, 5 figures, ACM Multimedia 2025 Dataset Track	None
CPEP: Contrastive Pose-EMG Pre-training Enhances Gesture Generalization on EMG Signals	2025-09-08	Show Hand gesture classification using high-quality structured data such as videos, images, and hand skeletons is a well-explored problem in computer vision. Leveraging low-power, cost-effective biosignals, e.g. surface electromyography (sEMG), allows for continuous gesture prediction on wearables. In this paper, we demonstrate that learning representations from weak-modality data that are aligned with those from structured, high-quality data can improve representation quality and enables zero-shot classification. Specifically, we propose a Contrastive Pose-EMG Pre-training (CPEP) framework to align EMG and pose representations, where we learn an EMG encoder that produces high-quality and pose-informative representations. We assess the gesture classification performance of our model through linear probing and zero-shot setups. Our model outperforms emg2pose benchmark models by up to 21% on in-distribution gesture classification and 72% on unseen (out-of-distribution) gesture classification.		None
Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning	2025-09-08	Show Generalized Category Discovery (GCD) is an emerging and challenging open-world problem that has garnered increasing attention in recent years. Most existing GCD methods focus on discovering categories in static images. However, relying solely on static visual content is often insufficient to reliably discover novel categories. To bridge this gap, we extend the GCD problem to the video domain and introduce a new setting, termed Video-GCD. Thus, effectively integrating multi-perspective information across time is crucial for accurate Video-GCD. To tackle this challenge, we propose a novel Memory-guided Consistency-aware Contrastive Learning (MCCL) framework, which explicitly captures temporal-spatial cues and incorporates them into contrastive learning through a consistency-guided voting mechanism. MCCL consists of two core components: Consistency-Aware Contrastive Learning(CACL) and Memory-Guided Representation Enhancement (MGRE). CACL exploits multiperspective temporal features to estimate consistency scores between unlabeled instances, which are then used to weight the contrastive loss accordingly. MGRE introduces a dual-level memory buffer that maintains both feature-level and logit-level representations, providing global context to enhance intra-class compactness and inter-class separability. This in turn refines the consistency estimation in CACL, forming a mutually reinforcing feedback loop between representation learning and consistency modeling. To facilitate a comprehensive evaluation, we construct a new and challenging Video-GCD benchmark, which includes action recognition and bird classification video datasets. Extensive experiments demonstrate that our method significantly outperforms competitive GCD approaches adapted from image-based settings, highlighting the importance of temporal information for discovering novel categories in videos. The code will be publicly available.		None
Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning	2025-09-08	Show The rapid growth of visual content consumption across platforms necessitates automated video classification for age-suitability standards like the MPAA rating system (G, PG, PG-13, R). Traditional methods struggle with large labeled data requirements, poor generalization, and inefficient feature learning. To address these challenges, we employ contrastive learning for improved discrimination and adaptability, exploring three frameworks: Instance Discrimination, Contextual Contrastive Learning, and Multi-View Contrastive Learning. Our hybrid architecture integrates an LRCN (CNN+LSTM) backbone with a Bahdanau attention mechanism, achieving state-of-the-art performance in the Contextual Contrastive Learning framework, with 88% accuracy and an F1 score of 0.8815. By combining CNNs for spatial features, LSTMs for temporal modeling, and attention mechanisms for dynamic frame prioritization, the model excels in fine-grained borderline distinctions, such as differentiating PG-13 and R-rated content. We evaluate the model's performance across various contrastive loss functions, including NT-Xent, NT-logistic, and Margin Triplet, demonstrating the robustness of our proposed architecture. To ensure practical application, the model is deployed as a web application for real-time MPAA rating classification, offering an efficient solution for automated content compliance across streaming platforms.	12 pages, 9 figures	None
Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization	2025-09-06	Show Human action recognition often struggles with deep semantic understanding, complex contextual information, and fine-grained distinction, limitations that traditional methods frequently encounter when dealing with diverse video data. Inspired by the remarkable capabilities of large language models, this paper introduces LVLM-VAR, a novel framework that pioneers the application of pre-trained Vision-Language Large Models (LVLMs) to video action recognition, emphasizing enhanced accuracy and interpretability. Our method features a Video-to-Semantic-Tokens (VST) Module, which innovatively transforms raw video sequences into discrete, semantically and temporally consistent "semantic action tokens," effectively crafting an "action narrative" that is comprehensible to an LVLM. These tokens, combined with natural language instructions, are then processed by a LoRA-fine-tuned LVLM (e.g., LLaVA-13B) for robust action classification and semantic reasoning. LVLM-VAR not only achieves state-of-the-art or highly competitive performance on challenging benchmarks such as NTU RGB+D and NTU RGB+D 120, demonstrating significant improvements (e.g., 94.1% on NTU RGB+D X-Sub and 90.0% on NTU RGB+D 120 X-Set), but also substantially boosts model interpretability by generating natural language explanations for its predictions.		None
TPA: Temporal Prompt Alignment for Fetal Congenital Heart Defect Classification	2025-09-05	Show Congenital heart defect (CHD) detection in ultrasound videos is hindered by image noise and probe positioning variability. While automated methods can reduce operator dependence, current machine learning approaches often neglect temporal information, limit themselves to binary classification, and do not account for prediction calibration. We propose Temporal Prompt Alignment (TPA), a method leveraging foundation image-text model and prompt-aware contrastive learning to classify fetal CHD on cardiac ultrasound videos. TPA extracts features from each frame of video subclips using an image encoder, aggregates them with a trainable temporal extractor to capture heart motion, and aligns the video representation with class-specific text prompts via a margin-hinge contrastive loss. To enhance calibration for clinical reliability, we introduce a Conditional Variational Autoencoder Style Modulation (CVAESM) module, which learns a latent style vector to modulate embeddings and quantifies classification uncertainty. Evaluated on a private dataset for CHD detection and on a large public dataset, EchoNet-Dynamic, for systolic dysfunction, TPA achieves state-of-the-art macro F1 scores of 85.40% for CHD diagnosis, while also reducing expected calibration error by 5.38% and adaptive ECE by 6.8%. On EchoNet-Dynamic's three-class task, it boosts macro F1 by 4.73% (from 53.89% to 58.62%). Temporal Prompt Alignment (TPA) is a framework for fetal congenital heart defect (CHD) classification in ultrasound videos that integrates temporal modeling, prompt-aware contrastive learning, and uncertainty quantification.		None
Net2Brain: A Toolbox to compare artificial vision models with human brain responses	2025-09-05	Show We introduce Net2Brain, a graphical and command-line user interface toolbox for comparing the representational spaces of artificial deep neural networks (DNNs) and human brain recordings. While different toolboxes facilitate only single functionalities or only focus on a small subset of supervised image classification models, Net2Brain allows the extraction of activations of more than 600 DNNs trained to perform a diverse range of vision-related tasks (e.g semantic segmentation, depth estimation, action recognition, etc.), over both image and video datasets. The toolbox computes the representational dissimilarity matrices (RDMs) over those activations and compares them to brain recordings using representational similarity analysis (RSA), weighted RSA, both in specific ROIs and with searchlight search. In addition, it is possible to add a new data set of stimuli and brain recordings to the toolbox for evaluation. We demonstrate the functionality and advantages of Net2Brain with an example showcasing how it can be used to test hypotheses of cognitive computational neuroscience.	Publi... Published in Frontiers in Neuroinformatics (2025), Article 1515873. Version of record: https://doi.org/10.3389/fninf.2025.1515873 4 Pages, 3 figures, submitted and accepted to CCNeuro 2022. For associated repository, see https://github.com/ToastyDom/Net2Brain Update 1: Changed Citation	Code Link
A Digital Machine Learning Algorithm Simulating Spiking Neural Network CoLaNET	2025-09-05	Show During last several years, our research team worked on development of a spiking neural network (SNN) architecture, which could be used in the wide range of supervised learning classification tasks. It should work under the condition, that all participating signals (the classified object description, correct class label and SNN decision) should have spiking nature. As a result, the CoLaNET (columnar layered network) SNN architecture was invented. The distinctive feature of this architecture is a combination of prototypical network structures corresponding to different classes and significantly distinctive instances of one class (=columns) and functionally differing populations of neurons inside columns (=layers). The other distinctive feature is a novel combination of anti-Hebbian and dopamine-modulated plasticity. While CoLaNET is relatively simple, it includes several hyperparameters. Their choice for particular classification tasks is not trivial. Besides that, specific features of the data classified (e.g. classification of separate pictures like in MNIST dataset vs. classifying objects in a continuous video stream) require certain modifications of CoLaNET structure. To solve these problems, the deep mathematical exploration of CoLaNET should be carried out. However, SNNs, being stochastic discrete systems, are usually very hard for exact mathematical analysis. To make it easier, I developed a continuous numeric (non-spiking) machine learning algorithm which approximates CoLaNET behavior with satisfactory accuracy. It is described in the paper. At present, it is being studied by exact analytic methods. We hope that the results of this study could be applied to direct calculation of CoLaNET hyperparameters and optimization of its structure.	This ... This preprint describes numeric model of learning process in the spiking neural network called CoLaNET. At present, much more advanced version of CoLaNET is proposed that makes the results reported here insignificant and, possibly, misguiding	None
UAV-Based Intelligent Traffic Surveillance System: Real-Time Vehicle Detection, Classification, Tracking, and Behavioral Analysis	2025-09-04	Show Traffic congestion and violations pose significant challenges for urban mobility and road safety. Traditional traffic monitoring systems, such as fixed cameras and sensor-based methods, are often constrained by limited coverage, low adaptability, and poor scalability. To address these challenges, this paper introduces an advanced unmanned aerial vehicle (UAV)-based traffic surveillance system capable of accurate vehicle detection, classification, tracking, and behavioral analysis in real-world, unconstrained urban environments. The system leverages multi-scale and multi-angle template matching, Kalman filtering, and homography-based calibration to process aerial video data collected from altitudes of approximately 200 meters. A case study in urban area demonstrates robust performance, achieving a detection precision of 91.8%, an F1-score of 90.5%, and tracking metrics (MOTA/MOTP) of 92.1% and 93.7%, respectively. Beyond precise detection, the system classifies five vehicle types and automatically detects critical traffic violations, including unsafe lane changes, illegal double parking, and crosswalk obstructions, through the fusion of geofencing, motion filtering, and trajectory deviation analysis. The integrated analytics module supports origin-destination tracking, vehicle count visualization, inter-class correlation analysis, and heatmap-based congestion modeling. Additionally, the system enables entry-exit trajectory profiling, vehicle density estimation across road segments, and movement direction logging, supporting comprehensive multi-scale urban mobility analytics. Experimental results confirms the system's scalability, accuracy, and practical relevance, highlighting its potential as an enforcement-aware, infrastructure-independent traffic monitoring solution for next-generation smart cities.	15 pa... 15 pages, 8 figures, 2 tables	None
Short-video Propagation Influence Rating: A New Real-world Dataset and A New Large Graph Model	2025-09-04	Show Short-video platforms have gained immense popularity, captivating the interest of millions, if not billions, of users globally. Recently, researchers have highlighted the significance of analyzing the propagation of short-videos, which typically involves discovering commercial values, public opinions, user behaviors, etc. This paper proposes a new Short-video Propagation Influence Rating (SPIR) task and aims to promote SPIR from both the dataset and method perspectives. First, we propose a new Cross-platform Short-Video (XS-Video) dataset, which aims to provide a large-scale and real-world short-video propagation network across various platforms to facilitate the research on short-video propagation. Our XS-Video dataset includes 117,720 videos, 381,926 samples, and 535 topics across 5 biggest Chinese platforms, annotated with the propagation influence from level 0 to 9. To the best of our knowledge, this is the first large-scale short-video dataset that contains cross-platform data or provides all of the views, likes, shares, collects, fans, comments, and comment content. Second, we propose a Large Graph Model (LGM) named NetGPT, based on a novel three-stage training mechanism, to bridge heterogeneous graph-structured data with the powerful reasoning ability and knowledge of Large Language Models (LLMs). Our NetGPT can comprehend and analyze the short-video propagation graph, enabling it to predict the long-term propagation influence of short-videos. Comprehensive experimental results evaluated by both classification and regression metrics on our XS-Video dataset indicate the superiority of our method for SPIR.		None
PRECISE-AS: Personalized Reinforcement Learning for Efficient Point-of-Care Echocardiography in Aortic Stenosis Diagnosis	2025-09-02	Show Aortic stenosis (AS) is a life-threatening condition caused by a narrowing of the aortic valve, leading to impaired blood flow. Despite its high prevalence, access to echocardiography (echo), the gold-standard diagnostic tool, is often limited due to resource constraints, particularly in rural and underserved areas. Point-of-care ultrasound (POCUS) offers a more accessible alternative but is restricted by operator expertise and the challenge of selecting the most relevant imaging views. To address this, we propose a reinforcement learning (RL)-driven active video acquisition framework that dynamically selects each patient's most informative echo videos. Unlike traditional methods that rely on a fixed set of videos, our approach continuously evaluates whether additional imaging is needed, optimizing both accuracy and efficiency. Tested on data from 2,572 patients, our method achieves 80.6% classification accuracy while using only 47% of the echo videos compared to a full acquisition. These results demonstrate the potential of active feature acquisition to enhance AS diagnosis, making echocardiographic assessments more efficient, scalable, and personalized. Our source code is available at: https://github.com/Armin-Saadat/PRECISE-AS.	To be... To be published in MICCAI 2025	Code Link
STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery	2025-09-02	Show Despite advancements in rehabilitation protocols, clinical assessment of upper extremity (UE) function after stroke largely remains subjective, relying heavily on therapist observation and coarse scoring systems. This subjectivity limits the sensitivity of assessments to detect subtle motor improvements, which are critical for personalized rehabilitation planning. Recent progress in computer vision offers promising avenues for enabling objective, quantitative, and scalable assessment of UE motor function. Among standardized tests, the Box and Block Test (BBT) is widely utilized for measuring gross manual dexterity and tracking stroke recovery, providing a structured setting that lends itself well to computational analysis. However, existing datasets targeting stroke rehabilitation primarily focus on daily living activities and often fail to capture clinically structured assessments such as block transfer tasks. Furthermore, many available datasets include a mixture of healthy and stroke-affected individuals, limiting their specificity and clinical utility. To address these critical gaps, we introduce StrokeVision-Bench, the first-ever dedicated dataset of stroke patients performing clinically structured block transfer tasks. StrokeVision-Bench comprises 1,000 annotated videos categorized into four clinically meaningful action classes, with each sample represented in two modalities: raw video frames and 2D skeletal keypoints. We benchmark several state-of-the-art video action recognition and skeleton-based action classification methods to establish performance baselines for this domain and facilitate future research in automated stroke rehabilitation assessment.	6 pages	None
Anisotropic Fourier Features for Positional Encoding in Medical Imaging	2025-09-02	Show The adoption of Transformer-based architectures in the medical domain is growing rapidly. In medical imaging, the analysis of complex shapes - such as organs, tissues, or other anatomical structures - combined with the often anisotropic nature of high-dimensional images complicates these adaptations. In this study, we critically examine the role of Positional Encodings (PEs), arguing that commonly used approaches may be suboptimal for the specific challenges of medical imaging. Sinusoidal Positional Encodings (SPEs) have proven effective in vision tasks, but they struggle to preserve Euclidean distances in higher-dimensional spaces. Isotropic Fourier Feature Positional Encodings (IFPEs) have been proposed to better preserve Euclidean distances, but they lack the ability to account for anisotropy in images. To address these limitations, we propose Anisotropic Fourier Feature Positional Encoding (AFPE), a generalization of IFPE that incorporates anisotropic, class-specific, and domain-specific spatial dependencies. We systematically benchmark AFPE against commonly used PEs on multi-label classification in chest X-rays, organ classification in CT images, and ejection fraction regression in echocardiography. Our results demonstrate that choosing the correct PE can significantly improve model performance. We show that the optimal PE depends on the shape of the structure of interest and the anisotropy of the data. Finally, our proposed AFPE significantly outperforms state-of-the-art PEs in all tested anisotropic settings. We conclude that, in anisotropic medical images and videos, it is of paramount importance to choose an anisotropic PE that fits the data and the shape of interest.	13 pa... 13 pages, 3 figures, 2 tables, to be published in ShapeMI MICCAI 2025	None
BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation	2025-09-01	Show Advances in AI generative models facilitate super-realistic video synthesis, amplifying misinformation risks via social media and eroding trust in digital content. Several research works have explored new deepfake detection methods on AI-generated images to alleviate these risks. However, with the fast development of video generation models, such as Sora and WanX, there is currently a lack of large-scale, high-quality AI-generated video datasets for forgery detection. In addition, existing detection approaches predominantly treat the task as binary classification, lacking explainability in model decision-making and failing to provide actionable insights or guidance for the public. To address these challenges, we propose \textbf{GenBuster-200K}, a large-scale AI-generated video dataset featuring 200K high-resolution video clips, diverse latest generative techniques, and real-world scenes. We further introduce \textbf{BusterX}, a novel AI-generated video detection and explanation framework leveraging multimodal large language model (MLLM) and reinforcement learning for authenticity determination and explainable rationale. To our knowledge, GenBuster-200K is the {\it \textbf{first}} large-scale, high-quality AI-generated video dataset that incorporates the latest generative techniques for real-world scenarios. BusterX is the {\it \textbf{first}} framework to integrate MLLM with reinforcement learning for explainable AI-generated video detection. Extensive comparisons with state-of-the-art methods and ablation studies validate the effectiveness and generalizability of BusterX. The code, models, and datasets will be released.		None
Anticipatory Fall Detection in Humans with Hybrid Directed Graph Neural Networks and Long Short-Term Memory	2025-09-01	Show Detecting and preventing falls in humans is a critical component of assistive robotic systems. While significant progress has been made in detecting falls, the prediction of falls before they happen, and analysis of the transient state between stability and an impending fall remain unexplored. In this paper, we propose a anticipatory fall detection method that utilizes a hybrid model combining Dynamic Graph Neural Networks (DGNN) with Long Short-Term Memory (LSTM) networks that decoupled the motion prediction and gait classification tasks to anticipate falls with high accuracy. Our approach employs real-time skeletal features extracted from video sequences as input for the proposed model. The DGNN acts as a classifier, distinguishing between three gait states: stable, transient, and fall. The LSTM-based network then predicts human movement in subsequent time steps, enabling early detection of falls. The proposed model was trained and validated using the OUMVLP-Pose and URFD datasets, demonstrating superior performance in terms of prediction error and recognition accuracy compared to models relying solely on DGNN and models from literature. The results indicate that decoupling prediction and classification improves performance compared to addressing the unified problem using only the DGNN. Furthermore, our method allows for the monitoring of the transient state, offering valuable insights that could enhance the functionality of advanced assistance systems.	Prese... Presented at IEEE RO-MAN 2025	None
Aligning Moments in Time using Video Queries	2025-09-01	Show Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task poses several challenges, such as the need for semantic frame-level alignment and modeling complex dependencies between query and target videos. To tackle this challenging problem, we introduce MATR (Moment Alignment TRansformer), a transformer-based model designed to capture semantic context as well as the temporal details necessary for precise moment localization. MATR conditions target video representations on query video features using dual-stage sequence alignment that encodes the required correlations and dependencies. These representations are then used to guide foreground/background classification and boundary prediction heads, enabling the model to accurately identify moments in the target video that semantically match with the query video. Additionally, to provide a strong task-specific initialization for MATR, we propose a self-supervised pre-training technique that involves training the model to localize random clips within videos. Extensive experiments demonstrate that MATR achieves notable performance improvements of 13.1% in R@1 and 8.1% in mIoU on an absolute scale compared to state-of-the-art methods on the popular ActivityNet-VRL dataset. Additionally, on our newly proposed dataset, SportsMoments, MATR shows a 14.7% gain in R@1 and a 14.4% gain in mIoU on an absolute scale over strong baselines.	11 pa... 11 pages, 4 figures, accepted at ICCV 2025	None
CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition	2025-08-31	Show Skeleton-based human action recognition leverages sequences of human joint coordinates to identify actions performed in videos. Owing to the intrinsic spatiotemporal structure of skeleton data, Graph Convolutional Networks (GCNs) have been the dominant architecture in this field. However, recent advances in transformer models and masked pretraining frameworks open new avenues for representation learning. In this work, we propose CascadeFormer, a family of two-stage cascading transformers for skeleton-based human action recognition. Our framework consists of a masked pretraining stage to learn generalizable skeleton representations, followed by a cascading fine-tuning stage tailored for discriminative action classification. We evaluate CascadeFormer across three benchmark datasets (Penn Action N-UCLA, and NTU RGB+D 60), achieving competitive performance on all tasks. To promote reproducibility, we release our code and model checkpoints.		None
FLUID: A Fine-Grained Lightweight Urban Signalized-Intersection Dataset of Dense Conflict Trajectories	2025-08-30	Show The trajectory data of traffic participants (TPs) is a fundamental resource for evaluating traffic conditions and optimizing policies, especially at urban intersections. Although data acquisition using drones is efficient, existing datasets still have limitations in scene representativeness, information richness, and data fidelity. This study introduces FLUID, comprising a fine-grained trajectory dataset that captures dense conflicts at typical urban signalized intersections, and a lightweight, full-pipeline framework for drone-based trajectory processing. FLUID covers three distinct intersection types, with approximately 5 hours of recording time and featuring over 20,000 TPs across 8 categories. Notably, the dataset averages two vehicle conflicts per minute, involving roughly 25% of all motor vehicles. FLUID provides comprehensive data, including trajectories, traffic signals, maps, and raw videos. Comparison with the DataFromSky platform and ground-truth measurements validates its high spatio-temporal accuracy. Through a detailed classification of motor vehicle conflicts and violations, FLUID reveals a diversity of interactive behaviors, demonstrating its value for human preference mining, traffic behavior modeling, and autonomous driving research.	26 pages, 14 figures	None
OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset	2025-08-28	Show Inspired by humans comprehending speech in a multi-modal manner, various audio-visual datasets have been constructed. However, most existing datasets focus on English, induce dependencies with various prediction models during dataset preparation, and have only a small number of multi-view videos. To mitigate the limitations, we recently developed the Open Large-scale Korean Audio-Visual Speech (OLKAVS) dataset, which is the largest among publicly available audio-visual speech datasets. The dataset contains 1,150 hours of transcribed audio from 1,107 Korean speakers in a studio setup with nine different viewpoints and various noise situations. We also provide the pre-trained baseline models for two tasks, audio-visual speech recognition and lip reading. We conducted experiments based on the models to verify the effectiveness of multi-modal and multi-view training over uni-modal and frontal-view-only training. We expect the OLKAVS dataset to facilitate multi-modal research in broader areas such as Korean speech recognition, speaker recognition, pronunciation level classification, and mouth motion analysis.	Accep... Accepted to ICASSP 2024	None
Leadership Assessment in Pediatric Intensive Care Unit Team Training	2025-08-28	Show This paper addresses the task of assessing PICU team's leadership skills by developing an automated analysis framework based on egocentric vision. We identify key behavioral cues, including fixation object, eye contact, and conversation patterns, as essential indicators of leadership assessment. In order to capture these multimodal signals, we employ Aria Glasses to record egocentric video, audio, gaze, and head movement data. We collect one-hour videos of four simulated sessions involving doctors with different roles and levels. To automate data processing, we propose a method leveraging REMoDNaV, SAM, YOLO, and ChatGPT for fixation object detection, eye contact detection, and conversation classification. In the experiments, significant correlations are observed between leadership skills and behavioral metrics, i.e., the output of our proposed methods, such as fixation time, transition patterns, and direct orders in speech. These results indicate that our proposed data collection and analysis framework can effectively solve skill assessment for training PICU teams.	This ... This paper is accepted by EgoVis Workshop at CVPR 2025	None
Development and Evaluation of an AI-Driven Telemedicine System for Prenatal Healthcare	2025-08-26	Show Access to obstetric ultrasound is often limited in low-resource settings, particularly in rural areas of low- and middle-income countries. This work proposes a human-in-the-loop artificial intelligence (AI) system designed to assist midwives in acquiring diagnostically relevant fetal images using blind sweep protocols. The system incorporates a classification model along with a web-based platform for asynchronous specialist reviews. By identifying key frames in blind sweep studies, the AI system allows specialists to concentrate on interpretation rather than having to review entire videos. To evaluate its performance, blind sweep videos captured by a small group of soft-trained midwives using a low-cost Point-of-Care Ultrasound (POCUS) device were analyzed. The system demonstrated promising results in identifying standard fetal planes from sweeps made by non-experts. A field evaluation indicated good usability and a low cognitive workload, suggesting that it has the potential to expand access to prenatal imaging in underserved regions.	Accep... Accepted at MICCAI 2025 MIRASOL Workshop, 10 pages, 5 figures	None
A Technical Review on Comparison and Estimation of Steganographic Tools	2025-08-26	Show Steganography is technique of hiding a data under cover media using different steganography tools. Image steganography is hiding of data (Text/Image/Audio/Video) under a cover as Image. This review paper presents classification of image steganography and the comparison of various Image steganography tools using different image formats. Analyzing numerous tools on the basis of Image features and extracting the best one. Some of the tools available in the market were selected based on the frequent use; these tools were tested using the same input on all of them. Specific text was embedded within all host images for each of the six Steganography tools selected. The results of the experiment reveal that all the six tools were relatively performing at the same level, though some software performs better than others through efficiency. And it was based on the image features like size, dimensions, and pixel value and histogram differentiation.	20	None
Boosting Micro-Expression Analysis via Prior-Guided Video-Level Regression	2025-08-26	Show Micro-expressions (MEs) are involuntary, low-intensity, and short-duration facial expressions that often reveal an individual's genuine thoughts and emotions. Most existing ME analysis methods rely on window-level classification with fixed window sizes and hard decisions, which limits their ability to capture the complex temporal dynamics of MEs. Although recent approaches have adopted video-level regression frameworks to address some of these challenges, interval decoding still depends on manually predefined, window-based methods, leaving the issue only partially mitigated. In this paper, we propose a prior-guided video-level regression method for ME analysis. We introduce a scalable interval selection strategy that comprehensively considers the temporal evolution, duration, and class distribution characteristics of MEs, enabling precise spotting of the onset, apex, and offset phases. In addition, we introduce a synergistic optimization framework, in which the spotting and recognition tasks share parameters except for the classification heads. This fully exploits complementary information, makes more efficient use of limited data, and enhances the model's capability. Extensive experiments on multiple benchmark datasets demonstrate the state-of-the-art performance of our method, with an STRS of 0.0562 on CAS(ME)$^3$ and 0.2000 on SAMMLV. The code is available at https://github.com/zizheng-guo/BoostingVRME.		Code Link
A Multimodal Handover Failure Detection Dataset and Baselines	2025-08-25	Show An object handover between a robot and a human is a coordinated action which is prone to failure for reasons such as miscommunication, incorrect actions and unexpected object properties. Existing works on handover failure detection and prevention focus on preventing failures due to object slip or external disturbances. However, there is a lack of datasets and evaluation methods that consider unpreventable failures caused by the human participant. To address this deficit, we present the multimodal Handover Failure Detection dataset, which consists of failures induced by the human participant, such as ignoring the robot or not releasing the object. We also present two baseline methods for handover failure detection: (i) a video classification method using 3D CNNs and (ii) a temporal action segmentation approach which jointly classifies the human action, robot action and overall outcome of the action. The results show that video is an important modality, but using force-torque data and gripper position help improve failure detection and action segmentation accuracy.	Accep... Accepted at ICRA 2024	None
Designing Practical Models for Isolated Word Visual Speech Recognition	2025-08-25	Show Visual speech recognition (VSR) systems decode spoken words from an input sequence using only the video data. Practical applications of such systems include medical assistance as well as human-machine interactions. A VSR system is typically employed in a complementary role in cases where the audio is corrupt or not available. In order to accurately predict the spoken words, these architectures often rely on deep neural networks in order to extract meaningful representations from the input sequence. While deep architectures achieve impressive recognition performance, relying on such models incurs significant computation costs which translates into increased resource demands in terms of hardware requirements and results in limited applicability in real-world scenarios where resources might be constrained. This factor prevents wider adoption and deployment of speech recognition systems in more practical applications. In this work, we aim to alleviate this issue by developing architectures for VSR that have low hardware costs. Following the standard two-network design paradigm, where one network handles visual feature extraction and another one utilizes the extracted features to classify the entire sequence, we develop lightweight end-to-end architectures by first benchmarking efficient models from the image classification literature, and then adopting lightweight block designs in a temporal convolution network backbone. We create several unified models with low resource requirements but strong recognition performance. Experiments on the largest public database for English words demonstrate the effectiveness and practicality of our developed models. Code and trained models will be made publicly available.	Doubl... Double-column format, 13 pages with references, 2 figures	None
Wound3DAssist: A Practical Framework for 3D Wound Assessment	2025-08-25	Show Managing chronic wounds remains a major healthcare challenge, with clinical assessment often relying on subjective and time-consuming manual documentation methods. Although 2D digital videometry frameworks aided the measurement process, these approaches struggle with perspective distortion, a limited field of view, and an inability to capture wound depth, especially in anatomically complex or curved regions. To overcome these limitations, we present Wound3DAssist, a practical framework for 3D wound assessment using monocular consumer-grade videos. Our framework generates accurate 3D models from short handheld smartphone video recordings, enabling non-contact, automatic measurements that are view-independent and robust to camera motion. We integrate 3D reconstruction, wound segmentation, tissue classification, and periwound analysis into a modular workflow. We evaluate Wound3DAssist across digital models with known geometry, silicone phantoms, and real patients. Results show that the framework supports high-quality wound bed visualization, millimeter-level accuracy, and reliable tissue composition analysis. Full assessments are completed in under 20 minutes, demonstrating feasibility for real-world clinical use.		None
A Novel Dataset for Video-Based Neurodivergent Classification Leveraging Extra-Stimulatory Behavior	2025-08-25	Show Facial expressions and actions differ among different individuals at varying degrees of intensity given responses to external stimuli, particularly among those that are neurodivergent. Such behaviors affect people in terms of overall health, communication, and sensory processing. Deep learning can be responsibly leveraged to improve productivity in addressing this task, and help medical professionals to accurately understand such behaviors. In this work, we introduce the Video ASD dataset-a dataset that contains video frame convolutional and attention map feature data-to foster further progress in the task of ASD classification. Unlike many recent studies in ASD classification with MRI data, which require expensive specialized equipment, our method utilizes a powerful but relatively affordable GPU, a standard computer setup, and a video camera for inference. Results show that our model effectively generalizes and understands key differences in the distinct movements of the children. Additionally, we test foundation models on this data to showcase how movement noise affects performance and the need for more data and more complex labels.		None
Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition	2025-08-24	Show Few-shot action recognition (FSAR) aims to classify human actions in videos with only a small number of labeled samples per category. The scarcity of training data has driven recent efforts to incorporate additional modalities, particularly text. However, the subtle variations in human posture, motion dynamics, and the object interactions that occur during different phases, are critical inherent knowledge of actions that cannot be fully exploited by action labels alone. In this work, we propose Language-Guided Action Anatomy (LGA), a novel framework that goes beyond label semantics by leveraging Large Language Models (LLMs) to dissect the essential representational characteristics hidden beneath action labels. Guided by the prior knowledge encoded in LLM, LGA effectively captures rich spatiotemporal cues in few-shot scenarios. Specifically, for text, we prompt an off-the-shelf LLM to anatomize labels into sequences of atomic action descriptions, focusing on the three core elements of action (subject, motion, object). For videos, a Visual Anatomy Module segments actions into atomic video phases to capture the sequential structure of actions. A fine-grained fusion strategy then integrates textual and visual features at the atomic level, resulting in more generalizable prototypes. Finally, we introduce a Multimodal Matching mechanism, comprising both video-video and video-text matching, to ensure robust few-shot classification. Experimental results demonstrate that LGA achieves state-of-the-art performance across multipe FSAR benchmarks.	Accepted by ICCV2025	None
Multi-Agent Visual-Language Reasoning for Comprehensive Highway Scene Understanding	2025-08-24	Show This paper introduces a multi-agent framework for comprehensive highway scene understanding, designed around a mixture-of-experts strategy. In this framework, a large generic vision-language model (VLM), such as GPT-4o, is contextualized with domain knowledge to generates task-specific chain-of-thought (CoT) prompts. These fine-grained prompts are then used to guide a smaller, efficient VLM (e.g., Qwen2.5-VL-7B) in reasoning over short videos, along with complementary modalities as applicable. The framework simultaneously addresses multiple critical perception tasks, including weather classification, pavement wetness assessment, and traffic congestion detection, achieving robust multi-task reasoning while balancing accuracy and computational efficiency. To support empirical validation, we curated three specialized datasets aligned with these tasks. Notably, the pavement wetness dataset is multimodal, combining video streams with road weather sensor data, highlighting the benefits of multimodal reasoning. Experimental results demonstrate consistently strong performance across diverse traffic and environmental conditions. From a deployment perspective, the framework can be readily integrated with existing traffic camera systems and strategically applied to high-risk rural locations, such as sharp curves, flood-prone lowlands, or icy bridges. By continuously monitoring the targeted sites, the system enhances situational awareness and delivers timely alerts, even in resource-constrained environments.	16 pa... 16 pages, 16 figures, 8 tables	None
Adversarial Illusions in Multi-Modal Embeddings	2025-08-24	Show Multi-modal embeddings encode texts, images, thermal images, sounds, and videos into a single embedding space, aligning representations across different modalities (e.g., associate an image of a dog with a barking sound). In this paper, we show that multi-modal embeddings can be vulnerable to an attack we call "adversarial illusions." Given an image or a sound, an adversary can perturb it to make its embedding close to an arbitrary, adversary-chosen input in another modality. These attacks are cross-modal and targeted: the adversary can align any image or sound with any target of his choice. Adversarial illusions exploit proximity in the embedding space and are thus agnostic to downstream tasks and modalities, enabling a wholesale compromise of current and future tasks, as well as modalities not available to the adversary. Using ImageBind and AudioCLIP embeddings, we demonstrate how adversarially aligned inputs, generated without knowledge of specific downstream tasks, mislead image generation, text generation, zero-shot classification, and audio retrieval. We investigate transferability of illusions across different embeddings and develop a black-box version of our method that we use to demonstrate the first adversarial alignment attack on Amazon's commercial, proprietary Titan embedding. Finally, we analyze countermeasures and evasion attacks.	In US... In USENIX Security'24	None
Structural Damage Detection Using AI Super Resolution and Visual Language Model	2025-08-23	Show Natural disasters pose significant challenges to timely and accurate damage assessment due to their sudden onset and the extensive areas they affect. Traditional assessment methods are often labor-intensive, costly, and hazardous to personnel, making them impractical for rapid response, especially in resource-limited settings. This study proposes a novel, cost-effective framework that leverages aerial drone footage, an advanced AI-based video super-resolution model, Video Restoration Transformer (VRT), and Gemma3:27b, a 27 billion parameter Visual Language Model (VLM). This integrated system is designed to improve low-resolution disaster footage, identify structural damage, and classify buildings into four damage categories, ranging from no/slight damage to total destruction, along with associated risk levels. The methodology was validated using pre- and post-event drone imagery from the 2023 Turkey earthquakes (courtesy of The Guardian) and satellite data from the 2013 Moore Tornado (xBD dataset). The framework achieved a classification accuracy of 84.5%, demonstrating its ability to provide highly accurate results. Furthermore, the system's accessibility allows non-technical users to perform preliminary analyses, thereby improving the responsiveness and efficiency of disaster management efforts.		None
Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detection	2025-08-22	Show Unmanned Aerial Vehicles (UAVs) have become increasingly important in disaster emergency response by enabling real-time aerial video analysis. Due to the limited computational resources available on UAVs, large models cannot be run independently for real-time analysis. To overcome this challenge, we propose a lightweight and efficient two-stage framework for real-time wildfire monitoring and fire source detection on UAV platforms. Specifically, in Stage 1, we utilize a policy network to identify and discard redundant video clips using frame compression techniques, thereby reducing computational costs. In addition, we introduce a station point mechanism that leverages future frame information within the sequential policy network to improve prediction accuracy. In Stage 2, once the frame is classified as "fire", we employ the improved YOLOv8 model to localize the fire source. We evaluate the Stage 1 method using the FLAME and HMDB51 datasets, and the Stage 2 method using the Fire & Smoke dataset. Experimental results show that our method significantly reduces computational costs while maintaining classification accuracy in Stage 1, and achieves higher detection accuracy with similar inference time in Stage 2 compared to baseline methods.		None
CoFE: A Framework Generating Counterfactual ECG for Explainable Cardiac AI-Diagnostics	2025-08-22	Show Recognizing the need for explainable AI (XAI) approaches to enable the successful integration of AI-based ECG prediction models (AI-ECG) into clinical practice, we introduce a framework generating \textbf{Co}unter\textbf{F}actual \textbf{E}CGs (i,e., named CoFE) to illustrate how specific features, such as amplitudes and intervals, influence the model's predictive decisions. To demonstrate the applicability of the CoFE, we present two case studies: atrial fibrillation classification and potassium level regression models. The CoFE reveals feature changes in ECG signals that align with the established clinical knowledge. By clarifying both \textbf{where valid features appear} in the ECG and \textbf{how they influence the model's predictions}, we anticipate that our framework will enhance the interpretability of AI-ECG models and support more effective clinical decision-making. Our demonstration video is available at: https://www.youtube.com/watch?v=YoW0bNBPglQ.	Demo paper, 5 pages	None