Fine-Grained Video Understanding

Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough for deployment. Amateur team sport is a useful, largely untested place to check that assumption: over eight million students played a school sport in the United States in 2024-25 alone, almost none of it filmed by more than a single fixed camera, with several candidate actors crowded into frame and no operator or second angle to fall back on. Using volleyball as a test case, we ask whether strong performance on general video and world-model benchmarks translates into reliable, per-player attribution once footage is this chaotic, turning footage into statistics through a chain of tasks from finding play boundaries to naming who did what. We evaluate four approaches (prompting and agentic reasoning over frontier vision-language models, classical computer vision with small trained specialists, self-supervised video world models, and manual annotation) at every stage, on 66 amateur matches with 46,648 human-labelled contacts, filmed under conditions no published benchmark uses. No single paradigm wins every stage, and static, single-frame computer vision is not competitive at any stage involving motion or identity. A prompted model segments matches well, yet a far smaller trained model beats it at spotting contacts for a fraction of the cost, and the sport's own rules recover rally outcomes the pixels cannot. Identity is where every automated approach struggles: a jersey number is a static fact temporal reasoning cannot recover if never visible, unlike sporting action, a repeated motor pattern a temporal model can exploit, which is why holistic reasoning improves event detection while identity stays unchanged. We close with where each approach earns its cost, and what transfers beyond volleyball to amateur sport.

Atomic activity understanding aims to recognize and localize structured traffic behaviors that jointly encode motion patterns and their grounding in road topology. Unlike conventional action recognition, atomic activities are multi-agent, multi-label, and topology-aware: multiple activities co-occur while many agents remain inactive. We introduce Action-Slot, a structured action-centric representation learning framework. Slot attention is widely used for object-centric decomposition, but its permutation-invariant design and object-level inductive bias are misaligned with atomic activity semantics. We reformulate slot learning as structured activity decomposition through three designs: (1) category-aligned action slots that anchor slots to predefined activity categories, (2) parallel spatio-temporal slot updating for holistic video-level reasoning, and (3) background and negative-slot regularization that enforces competition between foreground activities and irrelevant regions. Together these establish an activity-centric inductive bias that disentangles concurrent and asynchronous activities directly from raw video. Beyond recognition, the learned representations encode transferable spatio-temporal grounding signals. We further propose an attention-difference-based pseudo mask selection framework that suppresses false positives by measuring attention changes before and after candidate region removal, enabling weakly supervised localization without dense annotations. To support systematic evaluation, we introduce TACO, a balanced synthetic dataset with full atomic activity coverage and pixel-level annotations. Experiments on OATS, TACO, and annotated nuScenes show superior recognition, strong sim-to-real transfer, and state-of-the-art weakly supervised localization.

An assistant watching egocentric video should notice a mistake from past frames alone, before the next step begins, and keep working once the person recovers. A mistake changes the state of the work, so every later step has to be read against what was done rather than against the plan. The first-mistake protocol that current online methods report on cuts each recording at its first mistake, so a fixed-time rule that never looks at the video is right on every case. We evaluate on complete trials, where mistakes and recoveries arise naturally, under a validation false-alarm budget and against controls that use timing alone. PROVIA keeps two records apart: a factual state, a learned summary of the steps each actor performed, mistakes included, and the accepted progress, an exact posterior over the state of an automaton induced from correct demonstrations by Bayesian state merging and over the execution status of each actor. Procedure-state transitions occur only in the correct-status branch; the mistake and correction branches retain the source state. A sequential test turns the per-frame mistake probability into alarms. With one filter and one optimization rule, PROVIA ranks mistakes best among the evaluated controlled baselines on CaptainCook4D, IndustReal, HoloAssist and IMPACT-ego. At a validation budget of 0.1 false alarms per minute it recalls .154 against .128 on CaptainCook4D and .034 against .015 on HoloAssist, where it leads at every budget. The pipeline runs at 58-70 frames per second. The source code is available at https://github.com/Kratos-Wen/PROVIA.

No-reference video quality assessment (NR VQA) has recently seen promising progress with deep learning. However, video data is inherently large, and processing them with deep models incurs high computational cost. This challenge is particularly acute in VQA, where preserving original-resolution cues and dense temporal information is critical for accuracy. Existing efficiency-driven preprocessing strategies, such as fragmenting, reduce computation but alter the input data distribution, limiting effective reuse of pretrained video foundation models (ViFMs). To address these challenges, we propose \textbf{H}igh-\textbf{F}idelity \textbf{V}ideo \textbf{Q}uality \textbf{A}ssessment (\textbf{HFVQA}), a framework built on fixed-size spatio-temporal (ST) patches that is fully compatible with pretrained ViFMs. HFVQA samples ST patches across multiple scales, including the original resolution, with minimal temporal subsampling to preserve low-level quality cues and semantic context. To limit computation, HFVQA introduces a lightweight auxiliary network trained end-to-end with the ViFM encoder to learn \textit{VQA-specific saliency}. Distilled directly from quality supervision, this saliency captures task-specific importance patterns, reflecting that video quality perception is dominated by a small subset of spatio-temporal regions. By combining high-fidelity spatio-temporal cues with learned, task-specific saliency, HFVQA achieves SOTA performance on standard NR VQA benchmarks while processing as little as 12% of candidate ST patches, making high-fidelity ViFM-based VQA computationally tractable.

Emerging physical AI systems require low-latency, task-oriented video communication over unreliable channels. We propose a semantic-aware multi-level neural video coding method for robust low-latency video transmission over unreliable channels that are abstracted as multi-level packet erasure channels. Built upon the real-time DCVC-RT neural video codec, the proposed framework introduces a semantic- and feature-aware coding strategy that partitions encoded representations into packets carrying different levels of semantic and latent-feature importance and assigns these packets to different streams, each associated with a priority level when transmitted over unreliable communication channels. We also developed an error-resilient entropy model that removes inter-packet dependencies, allowing each packet to be decoded independently under packet losses. The complete system is trained end-to-end over the abstracted multi-level packet erasure channels, enabling learning of channel-aware representations together with importance-aware packet assignment while facilitating the network for differentiated packet prioritization. Experiments show that the proposed framework significantly improves robustness over baseline DCVC-RT under packet erasures, achieving graceful degradation in less important regions while better preserving task-relevant visual content.

Micro-actions are subtle, low-intensity non-verbal behaviors that provide cues to fine-grained human states, including emotions and intentions. Recognizing them remains difficult because they are brief, contain weak visual changes, and often exhibit similar motion patterns across categories. This paper addresses these challenges with a fine-grained micro-action recognition method that combines full fine-tuning of InternVideo2.5, hierarchical soft fusion, and a lightweight candidate-label reranker. For the long-tailed label distribution in MA-52, we use class-balanced sampling and inverse-frequency reweighting to reduce the effect of frequent classes during training. We fine-tune InternVideo2.5 end to end and attach coarse and group-conditional fine-grained classification heads to the shared video representation, improving the consistency between coarse and fine predictions. For ambiguous samples, the candidate-label reranker uses hard samples and video-label matching to focus on easily confused fine-grained actions. Experiments validate the proposed method, which achieves a 79.99% F1-mean on MA-52 and ranks first in the 3rd Micro-Action Analysis Grand Challenge at ACM Multimedia 2026.

In this paper, we propose ReactVAU, a Slow-Fast Decoupled Framework for real-time streaming Video Anomaly Understanding (VAU). Existing VAU methods rely on offline inference with global temporal sampling, which violates causality and prevents deployment in live surveillance streams. Conversely, general streaming video models satisfy causal access but dilute rare transient anomalies during memory compression and often invoke heavyweight MLLMs uniformly over long normal intervals. React VAU addresses this gap with three synergistic components: a lightweight Fast Detection Module based on Spatial Grid Folding (SGF) for continuous anomaly filtering; an Anomaly-Aware Persistent Memory (AAPM) that protects critical visual cues from temporal decay; and a heavyweight Slow Reasoning Module that remains dormant during normal streams and is awakened only by suspicious events for semantic verification and causal description. Extensive experiments on multiple benchmarks demonstrate that ReactVAU operates under strict streaming constraints while simultaneously achieving competitive performance in both anomaly detection and causal reasoning, alongside significantly enhanced computational efficiency by minimizing heavyweight MLLM invocations. Project page is available at https://huiyuiui.github.io/ReactVAU/

Personalized video recommendation predicts user preference at the video level, while temporal video grounding localizes query-relevant moments. However, strong localization does not establish whether the retrieved moment constitutes valid evidence for recommending the video to a particular user. We study counterfactual behavior-grounded evidence retrieval, which separates where personalized evidence occurs from whether such evidence exists and evaluates whether model predictions respond consistently when that evidence is replaced. We introduce CBGER-10K, containing 5,000 controlled factual--counterfactual pairs for 3,026 users, where each pair replaces only the focal behavior-supported segment while preserving the user, temporal position, and hard distractors. We further propose CBGER, a compact framework that decouples segment-level localization from video-level evidence estimation and learns both through structured counterfactual supervision. CBGER achieves $0.4432$ MRR, $0.6977$ Pair Accuracy, and $0.6987$ Intervention Consistency across five adapted personalized-highlight and temporal-grounding baselines. Notably, compared with QD-DETR, its MRR improvement is not statistically significant, while Pair Accuracy improves by $11.03$ points. These results show that accurate temporal localization does not necessarily imply reliable personalized evidence existence, motivating explicit evaluation of Whether alongside Where.

We propose a lightweight two-stage framework for real-time video anomaly detection. The first stage employs YOLO v11n-pose to detect persons and extract seventeen skeletal keypoints in a single forward pass. The second stage encodes each cropped person region through CLIP ViT-B/32 and computes cosine similarity against predefined textual descriptions of anomalous behaviors. This architecture eliminates the need for optical flow, standalone pose estimators, and density-based scoring modules. Experiments on CUHK Avenue, ShanghaiTech Campus, and a custom indoor dataset collected at Chulalongkorn University demonstrate an end-to-end throughput of approximately 51 FPS on an NVIDIA Titan XP GPU, a 3.36x speedup over the multi-feature baseline, while maintaining frame-level AUROC values of 89.26%, 70.26%, and 84.13%, respectively.

Visual data is typically a prerequisite for training existing video anomaly detection (VAD) methods. However, obtaining sufficient annotated anomaly data for training is challenging and not scalable due to the rarity of anomaly data and the wide variety of abnormal events. In this work, we advocate that the effectiveness of treating texts as video sequences for the VAD model and propose a novel Text-Driven Video Anomaly Detection (TD-VAD) approach to break visual dependence. In contrast to the anomaly video data, text descriptions of abnormal events are easy to collect, and their class labels can be directly derived. Specifically, our method utilizes video-like text descriptions with temporal characteristics generated by LLM to train a VAD model, without any reliance on target-domain anomaly data. To capture the long- and short-range temporal logic of events, we design the event evolution causal attention module to model contextual dependencies across time. During inference, considering the domain gap between the texts and video sequences, we use the frozen CLIP encoder to extract embeddings of video frames to align the text modality while retaining crucial visual information. Comprehensive experiments on two large-scale VAD datasets, XD-Violence and UCF-Crime, demonstrate that our method outperforms prior one-class and unsupervised VAD methods by a large margin.

Video anomaly detection (VAD) aims to identify and temporally localize abnormal events in videos. Supervised methods learn anomaly decision boundaries from target-domain annotations but require substantial in-domain data. Existing training-free methods leverage the rich semantic knowledge and reasoning capabilities of pretrained models to interpret visual content, yet these capabilities do not directly define an anomaly decision criterion: richer anomaly descriptions better capture hazard resemblance without resolving abnormality. To this end, we propose Contrastive Event Adjudication for training-free Video Anomaly Detection (CEAVAD), which shifts the unit of inference from isolated anomaly concepts to falsifiable event hypotheses and establishes an inference-time explanatory boundary through the interaction between competing explanations and video evidence. Specifically, CEAVAD first uses public-safety knowledge to construct hazard-benign event contrasts, pairing each hazard mechanism with a generic normal account and a mechanism-specific benign counterpart. It then determines whether the target interval better supports a hazard explanation or its benign competitor, yielding a revisable contrastive boundary proposal for the target. Finally, CEAVAD adjudicates between the competing explanations to determine whether the hazard hypothesis survives the video evidence, supporting both temporally localized anomaly detection and evidence-grounded explanations. Experiments on three widely used VAD benchmarks demonstrate that CEAVAD achieves state-of-the-art performance under the training-free paradigm.

The MeViS-Audio track asks a system to segment the objects described by a spoken motion expression throughout a video and to return empty masks when the described target is absent. We present a simple staged solution. Qwen3-ASR first converts speech into text. Several video mask tracks are then produced with complementary grounding and segmentation models. Instead of trusting a single prediction, we select the track that has the highest average mask agreement with the other candidates. A small set of explicit direction, count, and plural rules corrects queries that require more than ordinary single-object tracking. Finally, a video-level classifier combines visual, audio-visual, and within-video query scores to decide whether any target is present. The submitted system obtains 0.5952 J &F, 0.7931 no-target accuracy, 0.9205 target accuracy, and a final score of 0.769589. The challenge organizers notified our team that this result ranked first in the track.

Traffic surveillance cameras capture accidents continuously, yet converting raw CCTV footage into structured event records that pinpoint when, where, and what type of collision occurred remains unsolved at scale. The ACCIDENT @ CVPR benchmark evaluates exactly this joint prediction under a strict constraint: no labeled real-world training data is available. We introduce a training-free, two-pass coarse-to-fine pipeline that pairs a frozen Qwen3-VL-32B-Instruct vision-language model with YOLO11x object detection and BoT-SORT tracking. A first pass sparsely samples the full clip to anchor the collision moment in time; a second pass re-examines a tight window around that estimate using frames annotated with stable vehicle identities and normalized bounding-box coordinates, which gives the model both a visual overlay and an explicit numeric description of the same scene. On the official 2,027-clip real-CCTV test set, our system achieves a three-way harmonic mean score of 0.504, surpassing all organizer-published baselines including the best multi-model ensemble (0.412) by a 22% relative margin.

Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Traditional deep learning approaches are fundamentally limited by poor generalization across diverse scenarios. While multimodal agents offer a promising tool-learning paradigm for VAD, current systems relying on supervised fine-tuning struggle with complex orchestration, and standard reinforcement learning often causes premature termination due to coarse-grained outcome rewards. To address these challenges, we propose VTO, a process-supervised reinforcement learning framework. Moving beyond static tool usage, VTO enables the agent to dynamically explore and interact with the environment. Specifically, we introduce a foundation model-driven cognitive evaluator to provide context-aware semantic feedback, which is seamlessly integrated into a Process-Supervised Cognitive Alignment that delivers fine-grained, step-wise supervision. By explicitly penalizing logical truncation and rewarding complete causal chains, the agent optimizes its multi-step reasoning policy for interrelated tool orchestration. To support our proposed framework, we meticulously crafted VAD-Tool, a hierarchical visual tool set comprising 12 specialized vision tools spanning from entity tracking to high-stakes hazard detection, and established the corresponding benchmark for rigorous multi-step reasoning evaluation. Extensive experiments on VAD-Tool demonstrate that VTO significantly outperforms baselines, achieving up to a 10.2% absolute accuracy improvement in tool scheduling. Code and data are available at https://github.com/MICLAB-BUPT/VTO.

Audio-visual event perception (AVEP) determines which events occur in a video, when they occur, and whether they are audible, visible, or both. Training-free methods query new event vocabularies by matching frozen audio and visual features with text-encoded event names. However, related labels share evidence. An incorrect label can then score at least as high as a correct one. We call this a false co-activation (FCA). No scalar cutoff can reject the incorrect label while keeping every correct one. Class-specific thresholds may prevent that label from becoming a final prediction, but the FCA remains in the underlying score vector. We introduce SCoPE, a training-free framework in which all queried labels compete for shared evidence and each modality guides event selection in the other. We derive an exact condition for when this competition removes an FCA in a two-label fit. With identical frozen CLIP+CLAP backbones on LLP, SCoPE improves Type@seg by 7.45 points and Event@seg by 5.04 points compared with the reported AV$^2$A values. The same fixed configuration transfers unchanged to OV-AVEBench and VGGSound-AVEL100k.

Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals. Existing approaches exhibit a "when-what" dissociation: traditional DNN-based methods localize when anomalies occur but lack semantic understanding, whereas LLM-based methods explain what happens but neglect precise temporal grounding. We attribute this to the absence of a unified reasoning paradigm. Inspired by how humans inspect surveillance videos - glancing globally to form temporal hypotheses, scrutinizing suspicious segments, and thinking iteratively to correct errors - we study this global-to-local paradigm from two perspectives. We first propose Glance then Scrutinize (GtS), a training-free framework using static and dynamic textual guidance for coarse-to-fine anomaly grounding and understanding, balancing accuracy and speed. To break the ceiling imposed by frozen external modules, we further propose a tool-augmented agentic VAD method, where a multimodal large language model learns to invoke a video cropping tool, inspect densely resampled frames, and self-correct mislocalized hypotheses, via cold-start supervised fine-tuning followed by reinforcement learning with a joint answer-grounding reward. For training and evaluation, we extend our prior VAGU benchmark into VAGU-T (Video Anomaly Grounding, Understanding, and Thinking), comprising 7,567 real-world videos over 21 anomaly categories with human-validated grounding, explanations, QA pairs, and chain-of-thought tool-calling traces. We further introduce JeAUG, a metric jointly evaluating semantic interpretability and temporal precision. Experiments show that GtS substantially surpasses training-free baselines, while the agentic model delivers both higher accuracy and faster inference.

Humans understand anomalous events through a coherent perceptual process in which they identify the focal instance, follow its behavior as the event unfolds, and interpret why it violates the expectations of the surrounding scene. Video anomaly understanding (VAU) seeks to endow models with a similar capability, moving beyond deciding whether a video is anomalous toward explaining how the event develops and why it matters. Although recent vision--language models (VLMs) can generate detailed and plausible anomaly descriptions, their semantic fluency does not ensure that these interpretations remain grounded in the correct anomaly instance over time. Existing benchmarks typically evaluate tracking and semantic understanding through separate protocols, leaving such instance--semantic inconsistency largely unmeasured. We therefore introduce TAU-Bench, a track-centric benchmark for jointly evaluating anomaly instance tracking and fine-grained anomaly understanding. TAU-Bench contains 1,118 videos, 1,454 tracks, and 202,438 pixel-level masks spanning 49 event and 45 scene categories, together with track-centric annotations that connect instance-level identification, event-level understanding, and scene-level reasoning. To build TAU-Bench at scale, we developed an automated data engine integrating anomaly suitability filtering, anomaly instance track construction, hierarchical caption annotation, and human quality control. Evaluations across representative VLM families show that models producing plausible anomaly interpretations may still fail to localize and track the correct instance reliably, revealing a persistent gap between semantic reasoning and visual grounding. These findings therefore highlight instance-grounded evaluation as an important step toward more faithful and reliable VAU systems.

Video anomaly understanding (VAU) focuses on comprehensively interpreting abnormal events in videos, requiring models to identify anomalous occurrences, discover their supporting evidence, and explain the underlying causes beyond simple anomaly detection. Existing VAU methods often rely on specialized training or limited observations, restricting generalization or evidence coverage. Although single-agent alternatives support adaptive video observation, they still integrate exploration, observation, and decision-making within a unified reasoning process, offering limited role specialization and structured evidence coordination. To address these limitations, we present AgenticVAU, a training-free multi-agent framework that casts VAU as an explore--verify process, where the system first discovers potential anomalies and then verifies them through targeted observations. To achieve this, four specialized agents are introduced to handle visual-rule construction, search planning, video observation, and final decision, respectively. These agents communicate through an anchor registry, a shared evidence memory that binds each observation. Guided by this agent framework, AgenticVAU interleaves broad temporal exploration, dense local verification, and cross-interval comparison until sufficient evidence is collected. We conduct extensive experiments on the ECVA, UCF-Crime, and MSAD subsets of VAU-Bench, the results show that AgenticVAU outperforms zero-shot inference and reinforcement learning-based baselines, demonstrating the value of multi-agent collaboration for video anomaly understanding.

As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors as black boxes, while the latent forgery-discriminative knowledge inside them remains largely unexplored. Instead of continuing to rely on resource-intensive full-model retraining to steadily improve detection performance, we ask whether video forgery detection can also be achieved by uncovering and activating sparse forensic knowledge within the detector. We find that forgery-discriminative knowledge is not uniformly distributed across the full representation space, but is concentrated in a sparse set of functionally specialized neurons. Based on this insight, we propose a video forgery-intrinsic neuron discovery (V-FIND) framework. V-FIND first localizes critical layers that exhibit pronounced discrepancies between real and forged videos, and then identifies latent anchor neurons that consistently carry forgery-discriminative signals, organizing them into a compact forensic subspace. With the original backbone frozen and only a lightweight linear classifier trained, this subspace still delivers strong detection performance across multiple external benchmarks for generated videos. Further neuron intervention experiments provide direct evidence for the functional specificity of the discovered neurons. Overall, these results suggest that video forgery detectors contain sparse, extractable, and reusable forgery-discriminative knowledge, offering a new perspective on understanding and exploiting their intrinsic forensic capability.

Much of the recent progress in image and video recognition has come at the cost of memory: larger models, increased resolution, and longer temporal contexts. An inevitable component is the quadratic (or larger) growth of memory and compute based on image resolution, which is a property of the grid sampling used in convolutional networks and vision transformers. In this work we study residual networks whose convolutional blocks have logarithmic-square growth instead, enabling them to process very high-resolution video quickly. The key insight is to use a residual architecture's residual stream as a high-resolution buffer, to which convolutional blocks only read and write via log-polar image warp operations. Layers adaptively focus on different parts of each frame, with very high resolution only near the focus point. A complete high-resolution representation is built up in the residual stream, analogous to eye saccades creating a complete picture in biological vision, and a theoretical construction is presented that eliminates the quadratic dependency of the residual stream resolution. Experiments demonstrate that our proposed HiResNets learn to foveate around scenes similarly to human vision, and have superior performance in difficult egocentric video recognition tasks, especially egocentric video with small objects and fine-grained recognition.

Video Scene Procedure Planning (VSPP) supplies the target start-goal observations in advance, leaving open how a planner should act when the evidence must itself be retrieved. We introduce Cross-Video Scene Procedure Planning (CVSPP): given an answer-redacted start-goal query and K candidate videos, a model must retrieve the supporting video, localize the relevant window, and predict the action sequence. Two obstacles couple here. Same-task demonstrations share stages and windows, and an early hard selection passes the wrong scene chain to the planner. We build an eleven-source benchmark with typed negative roles, a fail-closed answer-leakage gate, and separate Evidence- and Plan-axis metrics. On its 14 source-horizon cells we adapt nine planner families against a majority-sequence floor. We then present One-Step Evidence Fusion (OSEF), which scores a query-conditioned cell-and-span lattice over all candidates and feeds the full soft lattice to the planner through a token-global adapter, cropping no window beforehand. OSEF ranks first on all six cells the benchmark certifies as method-rankable. On four matched same-task COIN and CrossTask cells it improves exact-video-and-plan success by 2.9-10.7 points over an enhanced hard-selection SOTA, and a component study assigns the largest single increment to the token-global interface. Five converted-source cells sit at or near the majority-sequence floor, the benchmark's remaining headroom. The supplementary package includes model constructors and evaluation code.

Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures. Most existing methods rely on holistic representations, which are insufficient for capturing subtle interactions and fine-grained semantics. While recent prompt-based approaches introduce disentanglement, they lack explicit semantic guidance, and methods based solely on visual or structured cues remain coarse-grained. In this paper, we propose Knowledge-guided Disentanglement with Atomic Actions (KDA), which leverages fine-grained semantic knowledge to enhance action representations and enable more precise disentanglement. Specifically, we use Large Language Models (LLMs) to decompose action labels into atomic actions, providing explicit spatial-temporal semantics. A Knowledge Injection Module (KIM) first integrates atomic action knowledge into video features. Based on this enhanced representation, a Knowledge Disentanglement Module (KDM) further disentangles atomic action knowledge to produce more precise semantic guidance for action disentanglement. A Knowledge Disentanglement Loss (KD Loss) is introduced to encourage clearer disentanglement of knowledge components within KDM. Extensive experiments demonstrate that KDA improves feature discriminability and achieves state-of-the-art performance on multi-label action recognition benchmarks. Moreover, KIM and KDM can be readily integrated into other methods, demonstrating strong generality.

Open-world video anomaly detection (OWVAD) is expected to detect events that match a user-specified definition of abnormality. This requirement is stronger than generic anomaly localization: in the same video, changing the definition should change which temporal regions are scored as anomalous. We show that current OWVAD evaluation largely fails to isolate this conditional behavior. Standard VAD metrics and the dynamic-definition protocol can be dominated by target-versus-normal separation, allowing models to obtain strong scores while remaining nearly insensitive to the queried definition. We call this failure mode definition blindness. To explain why it is missed, we decompose dynamic-definition evaluation into target-versus-normal detection and target-versus-other-anomaly discrimination, and find that the former receives 7.2-26.8$\times$ more weight across common VAD benchmarks. Motivated by this diagnosis, we introduce three definition-conditioned evaluation metrics, DC-Disc, DC-Det$Δ$, and DC-Sel$Δ$, which progressively remove normal-frame, generic-anomaly, and multi-event selection shortcuts. Experiments on UCF-Crime, XD-Violence, and MSAD reveal that several strong VAD, OWVAD, and general vision language model baselines localize anomalous moments but exhibit weak definition following, often with near-zero definition-response margins. To validate that the failure is actionable, we further introduce DeCoS, a definition-contrastive scoring rule that subtracts anomaly evidence shared across definitions. DeCoS improves the strongest baseline by 7.3-16.0 AUROC points on DC-Disc and 15.5-28.3 points on DC-Det$Δ$. Overall, our results argue that OWVAD should be evaluated as definition-conditioned anomaly scoring, not as anomaly detection under different prompt labels.

Action Quality Assessment (AQA) aims to objectively evaluate performance quality from action videos. Most existing methods follow a ``one-by-one'' paradigm, training a separate model for each action type. This setting limits real-world deployment, as it requires prior action-type knowledge to select the corresponding model and suffers from poor generalization across diverse actions. To address these limitations, we study the challenging task of all-in-one AQA, which aims to assess heterogeneous actions within a single unified model. We propose a novel Mixture of Action Knowledge Experts (MoAKE) framework, designed to mitigate negative knowledge transfer caused by large semantic discrepancies among actions. MoAKE learns complementary experts that capture diverse action patterns within a shared semantic space and dynamically aggregates their knowledge to adapt the assessment to the input action. Each expert is tailored with segment-aware prototypes to handle varying temporal lengths, together with an Adaptive Intra- and Inter-Segment Relationship Modeling (AIISRM) module to model multi-granularity temporal dynamics. Furthermore, we establish comprehensive benchmarks for all-in-one as well as zero/few-shot AQA. Extensive experiments on three long-term datasets demonstrate that MoAKE significantly outperforms existing methods in the all-in-one setting, while also achieving consistent generalization on three short-term datasets under zero/few-shot evaluation. Code is available at https://github.com/XuHuangbiao/MoAKE.

Training video anomaly detectors is challenging due to the difficulty and cost of annotating diverse and rare abnormal events. Although recent large vision-language models enable training-free inference, existing approaches mostly rely on holistic inference over sampled video and may miss context-specific anomaly cues. In this paper, we present CSI-VAD, a training-free video anomaly detector that identifies abnormal events across diverse contexts. The key idea is to decompose each video into three distinct contexts (environment, objects, time) and perform context-specific inference in separate branches. Because we ground anomaly judgments solely in context-specific visual cues, we do not require predefined text prompts describing abnormal events or dataset-specific tuning. Experiments on UCF-Crime and UBnormal show that CSI-VAD consistently improves over the direct holistic baseline and achieves competitive performance against existing methods, showing the advantage of structured context decomposition for training-free video anomaly detection.

Multi-object tracking (MOT) aims to localize multiple objects in videos while preserving their identities over time. Long-term identity preservation remains difficult when objects are small, densely distributed, and highly similar in appearance, as in bee swarm scenes. Existing trackers rely on re-identification (re-ID) models trained through single-instance assignment (instance-level querying). At inference, however, MOT requires global assignment between multiple trajectories and detections, corresponding to video-level querying. This training-inference mismatch can cause identity switches among visually similar objects. Existing approaches also often require substantial additional annotations to enhance appearance discrimination. We propose Video-Level Association re-ID (VLA-ReID), which reformulates re-ID as video-level association modeling. It uses aggregated historical trajectory features as queries and all current-frame detections as candidates, enabling direct optimization of their global association at each frame. In addition, Frame-Common Appearance Estimation (FCAE) estimates a common appearance direction from current-frame detections, while Common-Appearance Suppression (CAS) removes the corresponding component along this direction from trajectory and detection features. This amplifies discriminative differences among highly similar objects without additional annotations. Experiments on BEE24 show that VLA-ReID improves HOTA by 1.1, MOTA by 0.3, AssR by 2.6, AssA by 0.7, and IDF1 by 0.8 over state-of-the-art trackers, while reducing identity switches by 28%. These results demonstrate the effectiveness of video-level re-ID modeling for appearance-based association in MOT.

We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space and a softmax temporal attention in time. In each frame, SEMA attention applies a local window attention in parallel with a global averaging in a Mamba macro-architecture, which is called Mamba-like. Under certain rank conditions, we prove that the computationally cheaper split space-time attention is equivalent to full space-time attention. On benchmark K400 data sets, VideoSEMA out-performs heavier vision transformer and Mamba models. On benchmark SSv2 data, VideoSEMA leads in top-1 accuracy among models of similar parameter sizes. As image resolution scales up from standard $224^2$ to $1024^2$ on K400 and without fine-tuning, VideoSEMA degrades much more gracefully than VideoMamba in accuracy. It is promising to extend VideoSEMA to longer videos with a dilated/sparse temporal attention.

Detecting ambivalence and hesitancy (AH) in unconstrained video is challenging because the target signal is inherently ambiguous and expressed through subtle cross-modal incongruence rather than prototypical affect. We present CF-Net, a deep multimodal network submitted to the 3rd Edition of the AH Video Recognition Challenge (ABAW 11th, ECCV 2026), targeting the BAH dataset. CF-Net encodes visual, audio, and transcript streams with frozen SigLIP2, HuBERT, and DistilBERT backbones, normalises backbone features per speaker to reduce identity leakage, and fuses them via a ConflictFusion module that explicitly computes pairwise cross-modal incongruence. Training combines certainty-weighted focal loss, manifold mixup, and modality dropout; an auxiliary certainty-regression head uses ambiguity annotations to stabilise learning on genuinely borderline samples. CF-Net achieves a Macro F1 of 0.7155 on the BAH validation set and 0.7364 (AP = 0.7439) on the private challenge test set.

This article presents our results for the 11th Affective Behavior Analysis in-the-Wild (ABAW) competition. For multi-task learning with simultaneous prediction of valence, arousal, facial expressions, and action units on s-Aff-Wild2 dataset, we use frozen lightweight facial extractors, MT-EmotiDDAMFN and MT-EmotiEffNet-B0, with separate heads and systematic post-processing: temporal Gaussian smoothing, per-class expression bias, AffectNet blending, per-AU threshold tuning, and weighted backbone fusion. On the official validation set, our ensemble significantly exceeds the performance of the ConvNeXt baseline. For ambivalence/hesitancy video recognition on the expanded BAH dataset, we extend the audiovisual pipeline to video-level Macro F1 by late fusion of face, HuBERT audio, and RoBERTa text classifiers, temporal aggregation, and a global-text gate. Frame-level Weighted F1 on validation set rises from 0.74 in ABAW-8 to 0.79, while the best public-test video-level Macro F1 reaches 0.73. In both tasks, competitive performance is achieved without fine-tuning heavy backbones. These results indicate that systematic prediction calibration and lightweight multimodal fusion can rival substantially heavier end-to-end approaches while offering improved efficiency and deployment flexibility.

Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal alignment and exhibit fundamental limitations in multi-step reasoning and coordinated tool integration. We present TreeSoc, a structured reasoning framework that reformulates soccer video question answering as a hierarchical search problem rather than a single-pass prediction. Specifically, TreeSoc employs a dynamic depth-first search (DFS) mechanism that decomposes complex queries into sequentially ordered sub-tasks, enabling iterative reasoning refinement through explicit intermediate states. This tree-structured decomposition naturally supports adaptive tool routing, wherein domain-specific modules are selectively activated and their outputs incorporated at each reasoning node to produce contextually grounded predictions. On SoccerBench, TreeSoc achieves state-of-the-art performance, with accuracies of 85.2%, 87.4%, and 82.2% on TextQA, ImageQA, and VideoQA, respectively. Additionally, TreeSoc further demonstrates strong cross-domain generalization, attaining 74.16% accuracy on NExT-QA. These results establish structured, tool-augmented tree reasoning as an effective paradigm for robust video understanding. Code is available at: https://github.com/thanhnhan29/TreeSoc.

The evolving realism of AI-generated Videos (AIGC-V) is rapidly rendering traditional artifact-centric detection insufficient, necessitating a paradigm shift from low-level inspection to high-level semantic verification. This paper presents a comprehensive survey of AIGC-V detection, reframing the task as Factual Fidelity Verification, which asks whether the events, entities, and physical processes depicted in a video are consistent with real-world facts. To systematize this rapidly evolving field, we propose a Vision-Language Dual-View taxonomy that organizes existing methods into a hierarchical, four-layer landscape, spanning intrinsic cue analysis, spatiotemporal consistency modeling, cross-modal consistency reasoning, and language-guided world-level reasoning. This dual-view framing highlights a fundamental transition from artifact matching in traditional deepfake detection to evidence-based semantic verification enabled by vision-language models and agentic reasoning pipelines. Based on a systematic review of 221 works, we synthesize AIGC-V generation paradigms, survey the landscape of detection methods, and review evaluation metrics and benchmarks in line with proposed views. Finally, we discuss current challenges and identify promising directions toward robust, explainable, and trustworthy detection.

Maintenance of critical infrastructures, such as railways and power plants, is essential for ensuring operational safety and reliability. However, the declining number of skilled maintenance workers highlights the need to transfer expert know-how to less experienced workers. Previous studies have attempted to extract candidates of expert knowledge by comparing videos of manual-based work with those of expert workers, mainly focusing on differences in observable actions. However, expert know-how is often embedded not only in actions but also in contextual decision-making during task execution. This paper proposes a method that detects anomalous frames between two task videos to automatically extract candidate scenes containing expert-specific actions and contextual decision-making scenes. The method generates frame-wise visual descriptions using a vision-language model (VLM). Expert-specific actions are extracted based on frame similarities computed from description comparisons between two videos, while contextual decision-making scenes are extracted using segment similarities derived from intra-video self-similarity of the descriptions. In simulated distribution board maintenance experiments involving 27 task scenarios, the proposed method achieved extraction rates of 65% for action candidates and 61% for decision-scene candidates, improving over conventional methods that achieved 59% and 33%, respectively. These results demonstrate the effectiveness of the proposed approach in discovering candidate scenes containing expert know-how.

Weakly supervised video anomaly detection relies solely on video-level labels for training, making it difficult to accurately localize anomalous events in complex scenes. In real-world videos, anomalous behaviors exhibit large variations in appearance and temporal duration, while scene appearance and action dynamics are often tightly entangled. Consequently, existing models tend to rely on scene-related statistical cues rather than true behavioral deviations, resulting in unstable detection performance. To address this challenge, we propose a Structured Evidence Selection framework (SESAD) that reformulates anomaly detection as a structured reasoning process over clip-level visual evidence. Instead of directly mapping aggregated features to anomaly scores, SESAD reorganizes clip representations into semantically structured candidate evidence and performs context-conditioned selection under scene and action constraints. This mechanism adaptively emphasizes anomaly-relevant semantics while suppressing scene interference, thereby alleviating semantic entanglement under weak supervision. Furthermore, we introduce a lightweight geometric discrimination module that constructs a dual-prototype structure in the embedding space, enabling anomaly decisions through relative geometric relations. Extensive experiments on UBnormal, ShanghaiTech, and UCF-Crime show that SESAD achieves 67.92, 97.99, and 88.46 AUC, respectively, while maintaining high computational efficiency and overall consistently stable anomaly discrimination.

Video anomaly detection (VAD) is critical for automated surveillance but remains fragile under challenging conditions such as illumination variations, fast motion, and complex backgrounds when relying solely on visible light videos. To address these limitations, we propose EVAD, an event enhanced VAD framework that jointly exploits conventional video and event streams captured by bio inspired event cameras. Event sensors asynchronously capture brightness changes with high temporal resolution, offering robustness to motion blur and extreme lighting, and providing motion salient cues complementary to video based visual information. To support multi modal VAD research, we construct a large scale visible event benchmark comprising 6.3 billion events and 376,368 video frames collected under diverse illumination levels, motion patterns, and background complexities, filling the gap of realistic and scalable datasets for event based anomaly detection. Building upon this dataset, we design a contrastive multi modal pretraining framework to learn discriminative event representations by aligning semantic embeddings across event streams, visible videos, and textual descriptions. An adaptive fusion module then dynamically integrates event based temporal cues with video based spatial semantics, improving robustness to environmental disturbances. Experiments on benchmarks and the proposed TJUTCM Pha dataset demonstrate that E VAD consistently outperforms methods, validating the effectiveness of event-based sensing for VAD in real world scenarios.

Hand-object interaction (HOI) recognition requires capturing both hand manipulations and object transformations. However, existing video-language models often fall into shortcuts by relying on spurious correlations among hands, objects, or environmental context, rather than reasoning from the appearance and dynamics of hands and objects themselves. To address this limitation, we propose a new learning paradigm that combines (i) hand-object masked training, which enables robust reasoning from partial hand or object observations, and (ii) an HOI-dynamics-aware decoder that explicitly learns hand- and object-centric embeddings through auxiliary predictions of their locations and semantics, enhancing sensitivity to both cues. To systematically evaluate such cue-specific reasoning, we introduce Cue-Isolated HOI (CI-HOI), a new evaluation that assesses models' ability to predict actions from hand- and object-related cues independently. To enable CI-HOI, we curate the DEHOI testbed, which separates hand- and object-related observations for disentangled HOI evaluation through inpainting. Using DEHOI, we demonstrate both quantitatively and qualitatively that our training strategy exploits hand- and object-centric information more effectively than existing models. Our approach improves over existing models on DEHOI, standard action recognition, object state recognition, and even robot manipulation action recognition, leading to more robust HOI understanding.

Enhancing videos under extreme low-light conditions remains challenging due to the difficulty of balancing restoration quality and computational efficiency in resource-constrained settings. This paper introduces EeveeDark, a low-light video enhancement framework that combines the spatial richness of sensor-level RAW data with the temporal precision of event streams. Central to our model is a Binary Neural Network (BNN) architecture that reduces computational overhead by quantizing weights and activations while preserving detail. EeveeDark incorporates (i) modality-specific binary encoders for processing RAW frames and event data, (ii) a lightweight fusion block for integrating spatial and temporal cues, and (iii) an event-guided skip gating mechanism for dynamic spatiotemporal refinement. Experiments on synthetic and real-world datasets show that EeveeDark outperforms prior BNN-based methods and offers a favorable performance-efficiency trade-off compared to full-precision models. The project page is available at https://cyberiada.github.io/EeveeDark.

Event detection tasks in videos, the most important aspect of video surveillance, aim to detect events either at the pixel-level, frame-level, or clip-level. Plenty of methods intended for event detection in different environments, for various applications, and within different acquisition techniques were introduced. Naturally, the attempts were made as well to classify these algorithms in terms of detection of performance or in terms of real-time abilities. Nevertheless, the lack of a large-scale dataset as well as rigorous performance evaluation methods have biased such comparisons as well as the development of the methods. Given the diversity of existing approaches, we believe it is essential for researchers to position their work within such a rich landscape. Thus, we propose a rigorous framework for developing new methods in event detection for videos. Specifically, this framework is based on three main pillars: datasets, performance evaluation, and scenarios for deploying methods.

Modern video surveillance systems generate far more video streams than human operators can effectively monitor, making automated analysis essential for timely detection of security events. This paper presents a unified multi-task deep learning framework that simultaneously performs face recognition with zone-based authorization, automatic license plate recognition, weapon detection, fire and smoke detection, and human action recognition on a shared GPU platform. Among the integrated modules, two task-specific deep-learning models are proposed in this work to address scenarios that are insufficiently represented in publicly available datasets: a single-class weapon detector fine-tuned on a merged and relabeled dataset, achieving a mean average precision (mAP@0.5) of 0.947, and a SlowFast-R50 action recognition model trained on a purpose-built vandalism dataset comprising 614 video clips, achieving 94.33% classification accuracy. To improve robustness in continuous video, all detection modules are integrated into a temporal event-validation architecture based on multi-frame confirmation, confidence-weighted voting, and cascaded filtering, transforming frame-level predictions into reliable security events. Each module is evaluated independently on established public datasets (LFW, D-Fire, FIRESENSE, and UCF-Crime), followed by integrated end-to-end system evaluation. The proposed temporal validation strategy reduces the fire and smoke false-alarm rate from 52% to 4% and improves video license plate exact-match accuracy from 66.7% to 81.8%, while the complete framework maintains real-time operation with a per-frame latency below 100 ms on commodity hardware. These results demonstrate that combining specialized deep-learning models with temporal event validation provides an effective and practical solution for reliable real-time intelligent video surveillance.

As video generation paradigms evolve from localized manipulation to full-scene synthesis, AI-generated video detection becomes increasingly challenging, as forgeries exhibit coherent global structure and high perceptual realism. However, existing benchmarks are biased toward perceptual fidelity and primarily evaluate detectors based on perceptual artifacts, providing limited coverage of scenarios that require reasoning about violations of physical laws, structural coherence, or social logic. This dataset bias shapes current approaches and results in a Perception-Reasoning Gap: artifact-centric models capture low-level statistical irregularities yet lack semantic inference, whereas vision-language models perform semantic reasoning but remain insensitive to fine-grained forensic cues. To bridge this gap, we propose SafeGuard, a multi-agent framework that enables collaborative specialization between forensic perception and semantic reasoning. A hierarchical perceptual solver extracts fine-grained forensic evidence, while a self-reflective verifier enforces consistency between semantic inference and physical plausibility, forming an interpretable evidence chain. To support evaluation, we introduce SafeVid, a novel AI-generated video detection benchmark comprising 20K videos spanning 10 social risk categories, designed to evaluate physical plausibility, structural consistency, and the rationality of social behaviors. Extensive experiments demonstrate the generalization of SafeGuard, improving accuracy on SafeVid by +18.7% and consistently outperforming prior methods across four public benchmarks.

Video anomaly understanding (VAU) relies on sparse, context-dependent cues. However, existing passive paradigms suffer from observational aliasing, where static sampling fails to disambiguate semantically distinct events. To overcome this, we propose $Anom\text{-}π$, a closed-loop framework that reconceptualizes video understanding as an active sequential decision-making process within a dynamic environment. Inspired by human video-reviewing behavior, this framework unifies internal cognitive reasoning and strategic evidence acquisition into an interleaved policy, utilizing temporal atomic operators such as local backtracking, temporal expansion, and fine-grained sampling to endow the model with perceptual proactivity. To learn such complex interaction strategies under video-level weak supervision, we design Interactive Direct Preference Optimization (iDPO) to achieve trajectory-level policy alignment, guided by an Active Evidence Inquiry (AEI) utility that balances task success, informative evidence acquisition, and interaction cost. This approach enables the agent to learn to actively disambiguate hypotheses while suppressing redundant exploration. Extensive experiments demonstrate that our framework, with only 2B parameters, achieves highly competitive performance, significantly outperforming state-of-the-art large-scale VAU models in complex scenarios.

We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. Unlike previous benchmarks that primarily rely on text-based perturbations or adversarial questions while neglecting the consistency of visual backgrounds, VidPair-Halluc features video pairs with highly similar backgrounds but distinctly different foreground semantics, enabling precise attribution of model errors to genuine hallucination rather than background variation. The benchmark is constructed through PairFlow, a pipeline that leverages recent advances in text-to-image and video generation to systematically compose stories, generate coherent video clips, and assemble them into adversarial pairs. Covering both spatial and temporal reasoning across ten semantic aspects, VidPair-Halluc comprises 1K high-quality adversarial video pairs and 11K spatio-temporal QA pairs with control over background and foreground variations. Evaluations on mainstream LVMs show persistent difficulty with robust fine-grained video understanding in adversarial settings, and code and data are available at the https://jethrojames.github.io/VidPair-Halluc/.

Understanding facial expressions in videos requires modeling subtle and localized facial dynamics under unconstrained conditions. Although recent Vision Transformer (ViT)-based video models have shown strong performance through large-scale self-supervised pretraining, their attention mechanisms often emphasize dominant global motions and coarse temporal dynamics, limiting sensitivity to fine-grained facial variations. To address this limitation, we propose MiRA (Marginal-induced Attention Redistribution), a plug-in frame-marginal attention redistribution framework for ViT backbones that enhances spatio-temporal selectivity toward subtle facial dynamics without introducing additional trainable parameters. MiRA derives frame-level confidence and intra-frame concentration statistics from self-attention maps to estimate frame-wise marginal importance and redistribute attention toward spatiotemporally localized facial cues. We first introduce a principled exact mode based on post-softmax attention redistribution. To further improve efficiency, we propose flashLite mode, a lightweight pre-softmax approximation that integrates frame-marginal redistribution into FlashAttention kernels while preserving the effectiveness of the exact formulation. Experimental results on challenging Facial Expression Recognition (FER) benchmarks demonstrate consistent improvements over strong ViT baselines.

Despite the rapid advance of Multimodal Large Language Models (MLLMs) in high-level video understanding, a fundamental bottleneck remains: these models collapse complex human motion into coarse semantic labels. Existing benchmarks mostly focus on scene-centric events or local joint articulations, failing to probe global human motion in space over time (trajectory and orientation changes). We introduce HumanMoveVQA, the first comprehensive benchmark designed to evaluate global trajectory and orientation reasoning from an exocentric perspective. Our benchmark utilizes a first-frame anchored world coordinate system, preserving translation and rotation relative to a fixed starting point. We propose a scalable, multi-stage pipeline that lifts 2D video observations into world-consistent 3D motion tracks to generate over 10K structured question-answer pairs across seven reasoning categories, including motion aggregation, sequential ordering, and trajectory-level inference. Our extensive evaluation reveals a critical capability gap in state-of-the-art proprietary models on deep human motion understanding. However, we demonstrate that this is a learnable problem; by fine-tuning an open-source baseline with our targeted, world-consistent supervision, we achieve a significant improvement. HumanMoveVQA establishes a rigorous geometric foundation for developing next-generation, movement-aware video understanding models.

Video reasoning language models implicitly assume that every input frame is equally reliable. This leads to what we term the Blind Trust Problem: under realistic perturbations such as motion blur, glare, or occlusion, frontier video reasoning models can suffer 15-30%p accuracy drops on real-world embodied benchmarks, while remaining unaware that their visual evidence has been degraded. To address this challenge, we propose Robust-TO, an agentic video understanding framework that explicitly integrates per-frame trustworthiness into every stage of reasoning. Robust-TO organizes heterogeneous visual perception tools under a unified evidence interface. Each tool receives a sub-query derived from the original question and a set of trustworthy frames selected by the reliability-relevance score. It returns evidence in a shared format: a concrete prediction (e.g., a bounding box, motion trajectory, recognized text, or action label), temporal grounding, and a calibrated reliability score. During reasoning, these calibrated scores guide evidence weighting in a three-tier synthesis process (high/medium/low) and define a confidence-cost GRPO reward that jointly optimizes correctness, evidence reliability, and efficiency. On two video reasoning benchmarks spanning eight tasks, Robust-TO achieves 56.4% average accuracy on clean inputs, surpassing the strongest open-source baseline by 10.6%p and outperforming Gemini-2.5-Pro (46.2%). Under five realistic corruption types, Robust-TO maintains 54.3% average accuracy, 5.8%p above the strongest open-source baseline, while exhibiting the smallest clean-to-corrupted accuracy drop among all compared methods.

Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating its weights even during inference. This procedure does not require labels at test-time. This paper focuses on TTT for long-videos. A major concern with existing approaches is: 1) they perform TTT updates using a sliding window containing frames in the past, whose compute increases linearly with the size of window. This becomes computationally intractable when the videos are hours long. 2) TTT is performed even when temporally close frames look similar, thereby consuming a lot of compute. We present the Frame Forgetting Network (FFN) that: 1) operates on only three frames within the sliding window, namely the frame that exits, the current frame and the frame after that. The model still manages to retain temporal context and work for hours long-videos; 2) mathematically define a surprise metric: how much new information the incoming frame contains with respect to the past seen frame. This facilitates determining how to modify the effective window size during TTT and constitutes the core mechanism of an adaptive windowing algorithm. Additionally, we curate a dataset EpicTours containing up to 3 hour long videos of walking city-tours, whereas earlier datasets on this problem were only 5 min long. We demonstrate FFNs empirical effectiveness on dense-segmentation, video classification tasks, generalization to depth-estimation, and multi-hour long videos.

Egocentric video understanding is inherently limited by the narrow perspective of wearable cameras: a single viewpoint, a single modality, a single model cannot capture the full richness of human action. We argue that a truly expressive egocentric representation must subsume complementary knowledge across viewpoints, modalities, and foundation model representations, yet remain deployable from egocentric video alone. To this end, we introduce a hierarchical multi-teacher distillation framework that produces UNIEGO, a unified egocentric encoder trained with nine teachers spanning ego-exo viewpoints, RGB, depth, and skeleton modalities, and four foundation models. Rather than distilling directly from heterogeneous teachers whose incompatible architectures and feature geometries induce conflicting gradients, our framework interposes a layer of representation-specific Proxy models that translate diverse teacher knowledge into a homogeneous egocentric space. A second distillation stage, Selective Proxy Distillation (SPD), then adaptively selects, for each training sample, the subset of proxies that are both correct and confident, distilling exclusively from reliable supervision and suppressing erroneous signals. SPD is further stabilized by initializing UNIEGO as a learned convex combination of proxy parameters, placing the unified model in a well-conditioned region of the loss landscape before distillation begins. UNIEGO achieves state-of-the-art performance across three egocentric video understanding tasks - action recognition, video retrieval, and action segmentation on three challenging ego-exo benchmarks, outperforming naive multi-teacher distillation baselines and demonstrating that structured, proxy-mediated knowledge transfer yields richer and more discriminative egocentric representations.

Fine-grained action recognition in egocentric video is challenging for Vision-Language Models (VLMs): actions often differ only in small visual cues, and a single model tends to be biased toward a subset of these cues. We propose Divide, Deliberate, Decide, a fully-local, zero-shot multi-agent framework in which (i) a VLM orchestrator chunks the video and proposes a top-k candidate label list per segment, (ii) an ensemble of heterogeneous VLM specialists, drawn from different open model families, engages in a structured deliberation that includes a peer-consultation round of questions, and (iii) agent rankings are aggregated with a Borda count and the orchestrator re-ranks its own prediction in light of the specialists' evidence. The entire pipeline runs locally with no fine-tuning. Experiments show that our method positively improves zero-shot action recognition performance over the baseline, highlighting the influence of a heterogeneous deliberation step, showing that the gain stems from decorrelated model priors rather than from additional compute.

Translating video demonstrations into executable robot commands remains challenging because existing methods often fail to identify which objects are functionally involved in the demonstrated action. As a result, they may generate commands that are linguistically plausible but operationally ambiguous. We propose an object-centric video understanding framework that decouples action recognition from object identification to generate precise, grammar-free manipulation commands. Our approach integrates Temporal Shift Modules (TSM) for efficient spatio-temporal action classification with a novel \textbf{Object Selection} algorithm that identifies task-relevant objects through trajectory-based role classification, blur detection, and overlap minimization. The selected objects are then processed by Vision-Language Models (VLMs) for robust category recognition and zero-shot generalization. Evaluated on a modified Something-Something V2 dataset, our method achieves 86.79% action classification accuracy and BLEU-4 scores of 0.337 on standard objects and 0.261 on novel objects. These results improve over the strongest task-specific baseline by 80.2% and 143.9%, respectively. Larger gains are observed in METEOR and CIDEr, reaching 157.9% and 171.7% on novel objects. Across all semantic metrics, our approach consistently outperforms task-specific methods and remains competitive with, or surpasses, large general-purpose VLMs while retaining a modular, object-centric design.

Fine-grained understanding of operating room (OR) activity could enable workflow-aware assistance, yet remains difficult due to clutter, occlusions, and limited sensing. The prevailing approach to model this environment is scene graphs as an interpretable representation of OR interactions. Converting their frame-wise relational predictions into temporally extended, fine-grained actions however, is challenging without explicit temporal modeling. To enable a principled temporal evaluation of current OR understanding methods, we introduce the first action-centric benchmark built on a publicly available ego-exocentric OR dataset by defining a fine-grained, multi-role action taxonomy and generating dense action segments via distillation from ground-truth scene graph state changes. Experiments on this benchmark show that current scene graph prediction methods struggle to model temporal structure, even when adding explicit modeling through Graph Neural Networks. We therefore introduce a vision-only temporal model that outperforms graph-based methods significantly when using all available egocentric video as input. Building on this model we also introduce a novel multi- to single-view feature alignment strategy that improves single-view performance on multi-role action recognition, mitigating the need for extensive egocentric video capture. Benchmark and code will be released upon acceptance.

Video understanding is a crucial part of computer vision, with numerous application scenarios. With the increasing popularity of mobile devices, an increasing number of efforts are trying to deploy video understanding models on them. However, existing video understanding models are difficult to deploy due to their large size and prohibitive power consumption. Spiking Neural Networks (SNNs) have shown bioplausibility and low power advantages over Artificial Neural Networks (ANNs), especially on neuromorphic chips which are regarded as essential components of future mobile devices. However, excessively long conversion time-steps and severe performance degradation problems limit their application. To solve the problems above, we explore the application of SNNs on temporal action detection (TAD), which is an important task in video understanding, and propose the first SNN-based end-to-end TAD architecture coined as SpikeTAD. While maintaining extremely low power consumption, SpikeTAD achieves an average mAP of 67.2% in THUMOS14 and 37.42% in ActivityNet-1.3, demonstrating the feasibility of a low-power TAD model. Our code is available at https://github.com/MCG-NJU/SpikeTAD.

The dominant paradigm in video retrieval relies on embedding-based full-corpus scanning, which suffers from inherent computational inefficiency and the semantic asymmetry between information-dense videos and sparse textual queries. To bridge this gap, we introduce \textbf{MAVIS}, a novel multi-agent framework that rethinks retrieval as cooperative reasoning rather than brute-force search. MAVIS first bridges the granularity mismatch by parsing raw videos into a \textbf{Structured Semantic Library}, enabling explicit attribute-level indexing. During retrieval, a planner decomposes complex user intents into atomic sub-tasks, dispatching specialized agents to independently nominate candidates. Crucially, MAVIS employs a \textbf{Logic-aware Debate} mechanism with a strict veto protocol, where agents collaboratively prune logical mismatches to identify a compact set of ``controversial'' candidates for fine-grained verification. This agentic workflow effectively bypasses the inefficiency of full-library traversal. Extensive experiments on MSR-VTT, MSVD, and ActivityNet demonstrate that MAVIS achieves competitive performance without task-specific fine-tuning, offering a scalable and interpretable alternative to traditional dual-encoder approaches.

Emotional Video Captioning (EVC) is a challenging task that aims to generate factually accurate and emotionally rich descriptions for videos. Existing EVC methods leverage holistic visual features to mine global emotional cues, and then aggregate multimodal features to guide the emotional caption generation, which ignores the critical characteristic of the EVC task. Visual emotions are evoked by specific motivational causes, which are usually only implied in core video segments. The holistic mining brings significant information redundancy and inaccurate emotional cues. Thus, fine-grained visual cause extraction has a facilitative effect on both emotion perception and emotion-attributed caption generation. To this end, we propose a fine-grained emotion-cause pair extraction framework for emotion-attributed video captioning. Specifically, we learn pair-wise emotion and cause features in two rounds: 1) We propose a Concept-aware Visual Semantic Decomposition module to augment visual features by exploring scene, object, and motion concepts. Besides, to enhance emotional features, we propose a Visual-guided Emotion Interpretable Learning module, which guides emotion refinement with visual temporal dynamics, and augments the interpretable refinement process by reliable VAD-vector constraints. 2) We achieve emotion-cause pair extraction by cross-coupling the visual and emotional features before and after refinement, and leverage contrastive loss to achieve semantic forced alignment. Overall, our approach optimizes complex semantic understanding and emotion perception of videos, leading to a promising performance in emotional captioning. Extensive experiments on three challenging datasets demonstrate the superiority of our approach and each proposed module, e.g., achieving the best performances with +4.4% and +5.4% w.r.t. BLEU-2 and ROUGE-L, respectively, on the EVC-MSVD dataset.

Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events, including categories unseen during training. Existing methods primarily learn joint audio-visual representations in Euclidean space, but still face two significant challenges. First, the lack of supervision signals for unseen categories makes it difficult to maintain audio-visual consistency across multiple temporal scales. Second, the lack of hierarchical constraints between segment- and video-level semantics prevents the model from establishing semantic consistency across different levels. To address these challenges, we propose a hierarchical semantic constrained heterogeneous graph (HSCHG) for audio-visual event localization framework. We first construct a heterogeneous hierarchical graph in Euclidean space, which includes audio and visual segment nodes and their corresponding video-level nodes. We use multi-directional temporal edges to capture complete temporal information within each modality. Simultaneously, we employ a dual-threshold filtering gated fusion strategy, introducing cross-modal information only when the alignment confidence is high. Furthermore, we introduce bidirectional semantic constraints between segment- and video-level representations to achieve semantic consistency across different levels. Based on this, we map the multi-level audio-visual representations and text prototypes uniformly into hyperbolic space. We use a hierarchical entailment regularization loss to characterize the hierarchical relationships between videos and segments. Extensive experimental results show that our method outperforms existing methods on the OV-AVEL benchmark. Ablation studies further validate the effectiveness of our method.

AI-generated videos are becoming increasingly realistic, raising serious concerns about misinformation, content authenticity, and media trust. Reliable AI-generated video detection is therefore essential for multimedia forensics, yet remains challenging due to the need to capture spatial artifacts, temporal dynamics, and generalize to evolving generative models. In this paper, we explore reconstruction error as a discriminative forensic cue for AI-generated video detection. By reconstructing input videos with a pretrained WF-VAE, we observe that real and generated videos exhibit distinguishable frame-wise reconstruction error patterns, suggesting that reconstruction errors can reveal their distributional discrepancies. However, extending reconstruction-based image detection to videos is non-trivial, since video reconstruction errors are temporally organized across frames and require semantic context for effective interpretation. To address these challenges, we propose ReConFuse, a reconstruction-guided semantic fusion framework for video-level AI-generated video detection. ReConFuse extracts reconstruction error cues from WF-VAE reconstructed videos, aligns them with multi-frame semantic features, and uses a Mamba-based module to model temporal evolution for video-level classification. Experiments across multiple generators and evaluation settings demonstrate the effectiveness and strong generalization ability of ReConFuse.

In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data. To this end, we propose an Understanding-Enhanced Model Collaboration Method (UE-MCM) that combines efficient coarse-grained video understanding with accurate fine-grained action reasoning. Specifically, UE-MCM contains a small model branch and a large model branch. The large model branch focuses on whether the fine-grained action itself is executed incorrectly, while the small model branch jointly takes the coarse-grained video and fine-grained segment as input to identify actions that may be locally correct but inconsistent with the overall workflow. The small model branch is built on a CLIP4CLIP video encoder initialized from a CLIP model enhanced by Diffusion Contrastive Reconstruction, and the large model branch uses the Qwen3-VL Embedding model to extract high-capacity representations from fine-grained action segments. The small-branch prediction and the large-branch prediction are then adaptively fused by a lightweight collaboration gate. To handle the long-tailed distribution of mistake instances, we optimize the classifiers with complementary objectives, including reweighted cross-entropy, AUC-oriented learning, and label-aware adjustment. The resulting system balances speed and accuracy, making it effective for detecting subtle, rare, and ambiguous mistakes in egocentric instructional videos.

Video Moment Retrieval (VMR) targets to retrieve the specific moment corresponding to a sentence query from an untrimmed video. Although recent works have made remarkable progress in this task, they implicitly are rooted in the closed-set assumption that all the given queries as video-relevant\footnote{In this paper, we treat video-relevant query'' as in-distribution (ID) query'' and video-irrelevant query'' as out-of-distribution (OOD) query''.}. Given an OOD query in open-set scenarios, they still utilize it for wrong retrieval, which might lead to irrecoverable losses in high-risk scenarios, \textit{e.g.}, criminal activity detection. To this end, we creatively explore a brand-new VMR setting termed Open-Set Video Moment Retrieval (OS-VMR), where we should not only retrieve the precise moments based on ID query, but also reject OOD queries. In this paper, we make the first attempt to step toward OS-VMR and propose a novel model \textbf{OpenVMR}, which first distinguishes ID and OOD queries based on the normalizing flow technology, and then conducts moment retrieval based on ID queries. Specifically, we first learn the ID distribution by constructing a normalizing flow, and assume the ID query distribution obeys the multi-variate Gaussian distribution. Then, we introduce an uncertainty score to search the ID-OOD separating boundary. After that, we refine the ID-OOD boundary by pulling together ID query features. Besides, video-query matching and frame-query matching are designed for coarse-grained and fine-grained cross-modal interaction, respectively. Finally, a positive-unlabeled learning module is introduced for moment retrieval. Experimental results on three VMR datasets show the effectiveness of our OpenVMR.

We present the 1st-place solution to the ACCIDENT challenge at the CVPR 2026 AUTOPILOT Workshop, which asks for zero-shot prediction of accident timing, impact centroid, and collision type from CCTV footage. On a frozen Qwen3-VL-32B-Instruct checkpoint we build a three-stage pipeline (full-video joint prediction, time refinement, and single-frame grounding of the impact centroid), run the same pipeline a second time on a 235B Mixture-of-Experts sibling, blend the two outputs 9:1, and finally snap each predicted point onto the nearest vehicle detection. The final system reaches Public LB 0.55469 / Private LB 0.57080, roughly +0.21 over the strongest host baseline (Molmo-7B, 0.358) and wins the challenge. We ablate each component, report the negative results that shaped the final design, and release the code at https://github.com/fuumin621/cvpr2026-accident-1st-place-solution.

As Text-to-Video (T2V) generation models continue to evolve, the complexity of video evaluation necessitates a fine-grained assessment across various axes. To address this, recent works have focused on developing Multidimensional Video Reward Models (MVRMs), which decompose the evaluation process to better align with the multifaceted nature of human visual perception. However, training effective MVRMs is fundamentally challenged by the complex nature of video data. In this work, we identify a critical phenomenon termed Dimensional Heterogeneity: the reliability of a training sample can vary substantially across evaluation dimensions, meaning that a sample may provide reliable supervision for one objective while inducing high supervision risk for another. Consequently, prevailing data-centric methods that filter based on global scalar metrics are ill-posed for T2V tasks. To address this, we propose a disentangled influence framework that that efficiently estimates dimension-specific supervision risk. Leveraging this framework, we introduce two dimension-disentangled refinement strategies: Dimension-Disentangled Pruning, which removes extreme high-risk samples, and Dimension-Disentangled Reweighting, which softly down-weights high-risk supervision. Extensive experiments demonstrate that our disentangled strategies significantly outperform global filtering baselines, yielding reward models with superior alignment to ground truth.

UAV action recognition faces a deployment shift that standard benchmarks often obscure: a model trained on UAV footage captured from low-depression viewpoints may be required to recognize the same action classes from high-depression viewpoints. While the action labels remain unchanged, this shift alters body visibility, motion projection, and scene context, encouraging models to rely on viewpoint-specific shortcuts. We introduce UAV-OVO, an Out-of-Viewpoint generalization benchmark for UAV action recognition. UAV-OVO derives view scores from uncalibrated videos, uses a view-isolation band to assign low-depression videos to the training and in-distribution test splits while reserving high-depression videos for out-of-distribution testing, and constructs ID/OOD test sets matched by class distribution so that performance differences reflect viewpoint shift rather than label imbalance. Across representative video recognizers, UAV-OVO reveals a substantial ID/OOD gap: models that fit the low-depression training distribution well often fail to transfer to held-out high-depression views, exposing viewpoint shortcuts hidden by aggregate accuracy. We further propose LATER, LoRA-Anchored Test-time Re-centering, which first adapts the recognizer with Low-Rank Adaptation (LoRA) and then uses the learned LoRA subspace as a semantic anchor for online feature re-centering. Specifically, LATER projects target-domain displacement onto the orthogonal complement of the LoRA subspace before re-centering features, reducing viewpoint-induced drift while preserving task-relevant semantics. Together, UAV-OVO and LATER provide a controlled testbed and a practical adaptation method for viewpoint-robust UAV video understanding.

As AI-powered compliance monitoring becomes increasingly important in public governance and industrial safety, the ability to provide verifiable evidence and traceable accountability signals is essential. However, existing video anomaly detection datasets focus on event-level binary classification, lacking the rule-driven, explainable analysis required for real-world compliance scenarios. We introduce FoodMonitor, a benchmark for explainable compliance analysis in commercial kitchen surveillance. FoodMonitor comprises 477 video clips with 3,307 violation annotations across a dual-channel design covering both person-level and environment-level violations. Each annotation specifies which rule was violated, what non-compliant behavior occurred, and who committed it with frame-level bounding boxes. We establish a unified evaluation protocol with a two-stage matching mechanism that separately assesses spatial localization and semantic understanding, along with a composite metric ($C_{\text{score}}$) that balances environment and person detection performance. Systematic evaluation of several state-of-the-art multimodal large language models reveals that the best-performing model achieves only 0.360 $C_{\text{score}}$, with spatial localization and fine-grained rule understanding emerging as the primary bottlenecks. Our analysis identifies two distinct failure modes: localization-dominated errors and semantics-dominated errors, providing diagnostic insights for future model development.