Temporal Video Understanding

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 109% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 220

Sep 1, 2026cs.CV

TempCloze: Can Video-LLMs Identify the Missing Middle?

Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs. Given the beginning and ending clips of a video, models must identify the true missing middle from four candidates. TempCloze contains 1,521 carefully filtered videos from seven sources, mainly long-take and egocentric videos. We construct same-source distractors along three dimensions: Semantic asks what event should happen, Alignment probes when it should occur, and Progression tests how it should unfold, while shared scenes and objects reduce appearance cues. Our evaluation of 10 proprietary and 21 open-source Video-LLMs reveals Alignment as the primary bottleneck: models often recognize plausible semantic content and local event progression but struggle with temporal alignment. We further conduct error pattern and behavioral sensitivity analyses on TempCloze-Mixed and TempCloze-Hard with four representative models to examine where errors arise and how candidate order, context direction, visible span, frame density, and test-time scaling influence model choices.

Wenqi Pei, Henry Hengyuan Zhao, Yilai Liu +4

The University of Hong Kong · National University of Singapore · Peking University

Video-Language Model Evaluation Video-Language Models Temporal Video Understanding

Sep 1, 2026cs.CV

ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits

Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues like order, direction, and motion dynamics. Standard datasets mask this limitation by enabling models to exploit static spatial shortcuts. To systematically evaluate this, we introduce XTE-Bench, a diagnostic probe revealing that even large-scale video-language models struggle with basic temporal reasoning, indicating that parameter scaling alone is insufficient to resolve this flaw. To address this, we propose Cross-Modal Temporal Edits (XTE), a self-supervised framework that injects precise temporal supervision. By performing synchronized video-text transformations, XTE generates hard temporal negatives without manual annotation. We instantiate this with ViTAL-X, a lightweight model that equips frozen image-text backbones with temporal awareness while preserving their foundational spatial knowledge. Across six temporal benchmarks, ViTAL-X achieves state-of-the-art performance. Utilizing only 0.4B parameters and 1M training clips, ViTAL-X outperforms 7B-parameter models and surpasses baselines trained on 600x more data. These results demonstrate that targeted, high-quality temporal alignment provides a highly efficient alternative to pure scaling.

Sethuraman T, Savya Khosla, Onkar Kishor Susladkar +6

University of Illinois Urbana-Champaign · Adobe Research

Video-Language Model Evaluation Video-Language Models Temporal Video Understanding

Aug 30, 2026cs.CL

DVBench: Benchmarking MLLMs for Understanding Dynamic Charts and Narratives in Data Videos

While MLLMs have made significant strides in chart comprehension and video understanding, current evaluations largely isolate these capabilities, leaving a critical gap in understanding temporally evolving structured visual information. To address this gap, we introduce DVBench, a benchmark for evaluating MLLMs on data videos, a storytelling medium that integrates dynamic charts with structured narratives. We decompose data video understanding into five dimensions. DVBench comprises 300 real-world data videos and 1,000 human-verified QA pairs curated through a rigorous semi-automated pipeline. Extensive evaluations of nine MLLMs show that Gemini-3.1-Pro achieves the best overall performance, while Kimi-k2.5 is the strongest open-source model. We further identify two notable phenomena: open-source model performance does not scale strictly with parameter size, and narrative proficiency does not guarantee visual capability. Fine-grained analyses and ablation studies further reveal dimension-specific weaknesses and the effects of frame configurations and subtitle inputs, informing future MLLM development. DVBench is publicly available at https://bomiaowang.github.io/DVBench/.

Bomiao Wang, Zekai Shao, Jiexiang Lan +3

Fudan University · The Hong Kong University of Science and Technology (Guangzhou)

Video Understanding Video-Language Model Evaluation Chart Understanding Multimodal Model Evaluation Temporal Video Understanding

Aug 25, 2026cs.AI

VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models

Long-video understanding depends not only on the capability of a vision-language model (VLM), but also on how its limited context is constructed from a much longer video. Existing systems typically introduce hand-designed sampling, retrieval, memory, or agentic control strategies, making the context-construction program itself difficult to study as an independent optimization target. We introduce VideoHarness-RSI, a controlled framework that recursively searches executable context constructors around a frozen VLM while keeping the answering model and interface fixed. We study this baseline under complementary weak- and strong-initialization regimes. From a weak uniform constructor, recursive search progressively discovers more structured context-construction programs; from a stronger AKS harness, the same process further advances an already competitive hand-crafted frontier. The resulting harness retains its advantage under a matched cumulative visual-token control and transfers directly to additional long-video benchmarks without further search. Together, these results establish executable context construction as a distinct optimization layer and provide an auditable baseline for studying harness discovery, transfer, and efficiency around frozen VLMs.

Guoyang Xu, Hao Chen

Tencent

Program Synthesis Long-Video Understanding Long-Context VLMs Temporal Video Understanding

Aug 13, 2026cs.CV

EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory

Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video benchmarks. However, existing benchmarks rely predominantly on web-sourced videos that lack inter-clip spatiotemporal continuity, making it difficult to assess whether models can maintain consistent memory across days or weeks of real-world experience. We introduce EgoMonth, the first month-level egocentric video understanding benchmark. EgoMonth comprises over 300 hours of first-person daily-life recordings from 20 participants spanning 20 to 120 days, paired with 1,443 human-crafted multiple-choice question-answer pairs. We design a cognitively grounded 14-task evaluation framework organized into three hierarchical cognitive levels: Schema Consolidation, Episodic Indexing, and Cascading Reasoning. Evaluation of state-of-the-art open-source and closed-source MLLMs reveals that even the best-performing model, Gemini 2.5 Pro, achieves only 71.8% macro-average accuracy, remaining 22.4 percentage points below the corrected human baseline of 94.2%. Several models perform near or below the 25% chance level on tasks such as Route Reasoning, Cross-view Spatial Reasoning, and Direction Judgement, while even the strongest closed-source model remains substantially below human performance. These results indicate that current MLLMs function as lossy summarizers rather than faithful memorizers, highlighting the need for architectures with genuine long-term spatiotemporal memory.

Weitao Chen, Hu Jiaxin, Xie Tianyidan +15

Nanjing University, China · Huawei Technologies Co., Ltd., China · Tianjin University, China

Egocentric Video QA Video-Language Model Evaluation Egocentric Video Understanding Temporal Video Understanding

Aug 12, 2026cs.CV

A Hybrid Framework of Vision Transformer and Gated Recurrent Unit for Detection of Mosquito Diseases

Identifying dengue virus-infected mosquitoes from control mosquitoes is a major challenge in analyzing mosquito locomotion behavior due to the small size and complexity of the video background. Conventional AI methods are often unable to extract accurate features from video frames and produce erroneous features. In this study, a three-step framework is introduced: first, mosquitoes are identified and the background is removed using the YOLO 11M model, then visual features are extracted using the Vision Transformer (ViT), and finally the videos are classified with a convolutional GRU (ConvGRU) classifier. A comparative analysis of different models, including Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and their convolutional versions showed that the ConvGRU model achieved the best performance; it achieved 88.88% accuracy, 84.45% precision, 82.82% recall, and 82.81% F1 score. These results demonstrate that combining convolutional models with sequence-based networks, especially in the ConvGRU model, allows the simultaneous extraction of precise spatial features and long-term temporal dependencies from mosquito movements. Finally, the proposed framework provides a reliable solution for analyzing mosquito behavior in complex environments.

Danial Sharifrazi, Saadat Behzadi, Nouman Javed +3

Convolutional RNNs Animal Behavior Analysis Temporal Video Understanding

Aug 11, 2026cs.CV

FUSE: Frame-Unified Stress Estimation from Facial Video

Automatic stress detection from facial video offers a practical path to non-intrusive affect monitoring, yet existing video-based approaches commonly decompose full recordings into short temporal windows before classification. This design introduces additional choices regarding window length, overlap, and aggregation, while limiting direct analysis of temporal information across the entire recording. In this study, we present FUSE (Frame-Unified Stress Estimation), a facial-video stress detection framework that processes complete recordings as a single input without temporal windowing or external segmentation. The name reflects the defining operation of the method: rather than dividing a recording into short clips, all frames are fused into one unified two-dimensional representation from which the stress state is estimated. This unification is realized by folding the temporal dimension into the channel dimension of the spatial representation, and the resulting high-dimensional input is processed using a unified asymmetric-attention architecture. At a temporal stride of t = 1, FUSE retains the full 120-second recording as one input, corresponding to 3,600 frames at 30 fps. Experiments on a 58-subject stress dataset using a stratified subject-level protocol evaluate seven temporal-stride configurations, ranging from full-frame input to sparse subsampling. FUSE achieves the highest test accuracy of 69.44% at t = 15, while the full-frame configuration remains competitive at 69.03%. Across the stride range, computational cost varies from 12.48 to 348.78 GFLOPs, showing the trade-off between temporal density and efficiency. These results demonstrate that temporal windowing is not required for effective facial-video stress detection in this setting, and that complete-recording inference can be achieved within a single unified architecture.

Stefanos Gkikas, Thomas Kassiotis, Yang Guo +2

Honda Research Institute Japan Wako City, Japan · Department of Electronic Engineering Hellenic Mediterranean University Chania, Greece · Faculty of Information Science and Engineering Ocean University of China Qingdao, China

Emotion Recognition Temporal Video Understanding

Aug 10, 2026cs.CV

From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning

Detecting a traffic anomaly does not establish whether a video-language model can explain what happened, localize it in time, or identify its causes. We introduce TAR (Traffic Anomaly Reasoning) and TAR-Bench, paired resources for training and evaluating these complementary capabilities across 10 tasks spanning question answering, temporal reasoning, and scene understanding. TAR contains 44,040 automatically generated annotations with chain-of-thought traces for 3,670 CCTV videos from eight public datasets. TAR-Bench provides 960 human-curated annotations for 80 held-out clips from 17 public YouTube videos. Evaluation of eleven vision-language models reveals a gap between question-answering performance and temporal or scene reasoning. Progressively adding task groups during supervised fine-tuning improves aggregate performance on both Cosmos-Reason2-8B and Qwen3-VL-8B-Instruct. Training on all 10 tasks raises their mean benchmark scores from 34.3 to 55.7 and from 30.9 to 53.9, respectively. These results support joint training across complementary tasks as a promising approach to traffic anomaly understanding, while highlighting persistent limitations in temporal precision and causal attribution. TAR and TAR-Bench serve as the official training and in-domain evaluation resources for AI City Challenge 2026 Track 3.The dataset is available at https://huggingface.co/datasets/nvidia/PhysicalAI-Traffic-Anomaly-Reasoning

Han Zhang, Yilin Zhao, Zaid Pervaiz Bhat +5

NVIDIA · Santa Clara University

Video-Language Model Evaluation Video Anomaly Detection Temporal Video Understanding Anomaly Detection

Aug 9, 2026cs.CV

Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline

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.

Dipit Saha, Shah Mohammad Abdul Mannan, Mohammad Raihan Rashid +2

Bangladesh University of Engineering and Technology

Temporal Video Understanding

Aug 9, 2026cs.CV

VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language Models

Large vision-language models (LVLMs) have demonstrated strong performance in open-ended video understanding, yet they remain prone to fluent responses unsupported by video evidence. Existing training-free methods typically apply a globally fixed visual intervention or construct a contrastive branch through input perturbation. The former cannot accommodate video-dependent fusion paths, while the latter can be compensated by cross-frame redundancy. We therefore propose Video-Adaptive Debiasing via Evidence Reweighting (VADER), a training-free framework with two complementary modules. Visual Focus Reallocation (VFR) automatically instantiates an intervention policy for each video-question input: it diagnoses layer-wise visual-to-text evidence flow, determines where to intervene, and derives how strongly to reallocate pre-softmax attention from system-token to video-token blocks. Selective Evidence Erasure (SEE) independently masks high-importance visual tokens in every frame, constructing a prior-biased branch that is difficult to compensate through neighboring frames. Contrastive decoding then down-weights predictions that remain confident after selective evidence erasure. Across multiple VideoLLMs, VADER yields substantial improvements on event-level grounding and temporal consistency; on LLaVA-Video-7B, it reaches 72.60% accuracy on EventHallusion.

Dong Xing, Jiaxin Chen, Hang Yang +3

Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences Changchun, Jilin 130033, China · University of Chinese Academy of Sciences, Beijing 100049, China · City University of Hong Kong, Hong Kong, China

Video-Language Models VLM Hallucination Mitigation Temporal Video Understanding

Aug 7, 2026cs.CV

CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition

Real-time human action recognition on Internet-of-Things (IoT) edge devices requires models that capture rich spatio-temporal cues within strict latency, memory, and power envelopes. Current 3D CNNs, video transformers, and shift-based ViT deliver high accuracy but come at computational costs that preclude edge IoT deployment. This paper proposes CoDAT, a Collaborative Dual-Attention Transformer that replaces conventional multi-head attention with a lightweight dual-branch module: Spatial Convolutional Attention (SCA) for local aggregation and Strided Single-Head Attention (SSHA) for global context. SSHA jointly compresses the spatial resolution and channel dimensions of the query, key, and value tensors via stride-based sparse projection, then fuses the resulting global and local features at a markedly reduced cost. To enable temporal communication across frames, a parameter-free TShift module is embedded in each block. Extensive experiments on Jetson AGX Orin and Raspberry Pi 5 demonstrate that CoDAT achieves an energy-accuracy balance in both image and action recognition. On ImageNet-1K, CoDAT-M runs 2x faster than EfficientViT384 and FastViT-S12 at comparable accuracy, and CoDAT-L matches ViT-S with 3x fewer parameters at 2x higher throughput. On Kinetics-400 and MA-52, CoDAT achieves competitive Top-1 accuracy against state-of-the-art CNN, transformer, and hybrid baselines while running up to 2.9x faster than VSwin-T, 2x faster than ViT-Temporal-Shift variants, and 5x faster than UniFormer-B. On UCF-101, CoDAT-S384 matches TokShift and LAPS while being 6x faster and requiring up to 13x fewer FLOPs, establishing an efficiency-accuracy balance for real-time action recognition in edge IoT perception systems. Code is available at https://github.com/novendrastywn/CoDAT .

Novendra Setyawan, Chi-Chia Sun, Mao-Hsiu Hsu +3

Department of Electro-Optics, National Formosa University, Huwei 632301, Taiwan · Department of Electrical Engineering, University of Muhammadiyah Malang, Malang 65144, Indonesia · Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei 106335, Taiwan +1

Edge Inference Efficient ViTs Video Action Recognition Temporal Video Understanding

Aug 6, 2026cs.AI

The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping

Real-world video benchmarks provide broad coverage, but their fixed clips entangle event count, rate, duration, and visual complexity, making failure modes hard to isolate. While existing programmatic benchmarks offer better control, they score only the final answer rather than auditing reported events against executable ground truth. To bridge this gap, we introduce trace-grounded parametric profiling for event counting in three controlled video tasks: bouncing-ball wall contacts, visual blinks, and categorical state transitions. Across 2,190 videos, we vary event count N and frequency F while holding rendering fixed. Each video includes an executable event trace for capability-surface estimation and timestamp-level evaluation. Our results reveal a staged temporal failure. At an 80% reliability threshold, Gemini 3.6 Flash reliably counts persistent state transitions up to 12 events at 0.5 and 1.0 Hz, yet demonstrates no reliable positive-count region for transient blinking events. Thus, event representation dictates whether a model initially accesses evidence -- a limitation that compounds as count and frequency increase. In the high-count, high-frequency regime, only 0.2% of final counts are correct and the model recovers just 18.1% of true events. To test if visual access is the primary bottleneck, we increase sampling rate. Although this boosts Bounce Ball accuracy from 19.6% to 29.3%, the reported sequence agrees with ground truth only 3.7% of the time. Extra frames can therefore inflate final scores without producing faithful event recovery. Different prompting strategies yield similarly limited gains, and real-world video evaluations show the same concentration of success at low event counts. Ultimately, trace-grounded profiling shifts video evaluation from aggregate accuracy metrics to a detailed diagnostic of where temporal reasoning fails.

Sarvesh Baskar, Zikui Cai, Shayan Shabihi +5

University of Maryland, College Park, USA · Scale AI, USA

Video-Language Model Evaluation Temporal Video Understanding

Aug 6, 2026cs.CV

ChronoVision: Temporal Reasoning via Latent State Reconstruction

Multimodal large language models excel at passive perception but struggle with complex visual cognitive tasks requiring multi-step temporal reasoning. This degradation largely stems from the inherent ambiguity of language-based reasoning, which often fails to accurately articulate continuous visual transformations. To address this, we propose ChronoVision, a multimodal framework designed to align visual logic with latent imagery. During supervised fine-tuning, a Reconstructive Visual Head predicts the latent representation of the final transformed state, while an ROI Attention Locating module focuses the model on key visual evidence via semantic span queries. In post-training, we apply reinforcement learning with an implicit process grounding mechanism, guided by a composite reward function that evaluates outcome correctness, latent process alignment, and unsupervised visual focus. Furthermore, we introduce Vbvr-VQA, a novel dataset that evaluates temporal tracking by reformulating video reasoning into a strict image-ordering task. Experiments demonstrate that ChronoVision achieves state-of-the-art performance on Vbvr-VQA with 74.8% in-domain and 71.6% out-of-domain accuracy, alongside a strong 55.0% accuracy on IntPhys2, a highly challenging cross-domain benchmark.

Yifan Shen, Jian Xu, Boyi Li +6

University of Illinois Urbana-Champaign · PediaMed AI · University of Pennsylvania

Multimodal Large Language Models Latent Visual Reasoning Video Reasoning Temporal Video Understanding

Aug 6, 2026cs.CV

DynaPix: Can Vision-Language Models Identify the Exact Future?

Acting in a physical scene requires knowing its real later state, not a plausible one. Current evaluations often accept words or a realistic-looking image, so the predicted state is never checked against the true one. We introduce DynaPix (Dynamic Pixels), a benchmark that makes prediction checkable. Given a video clip that stops before a key event and a question about a later moment, a model must pick the true future image from close candidates or a large gallery. The scenes come from a physics simulator, so the correct image and its time are known exactly and the wrong options are deliberately similar. Models often succeed when a visible event marks the target moment, but are near chance when only elapsed time marks it. Gallery search is harder still, as the true image rarely ranks first. People handle the elapsed-time items well, so the difficulty lies with the models, not the questions. Training on scene accounts drawn from the simulator's true record, not a teacher's guess, repairs much of this but not the longer elapsed time case. DynaPix thus exposes a temporal-anchoring gap: models attach a prediction to an event far better than to time itself.

Thong Nguyen, Vinh-Hien Do, Quynh Vo +2

Centre for AI Research, VinUniversity · National University of Singapore

VLM Evaluation Vision-Language Models Video Prediction Temporal Video Understanding

Aug 5, 2026cs.CV

Persistent Object Narratives for Token-Efficient Video Language Models

Video large language models (Video-LLMs) have made strong progress in open-ended video understanding. However, their visual interfaces remain token-intensive and provide limited explicit structure for linking recurring object evidence across time. We introduce SlotNarrative, a slot-based interface that organizes a video into persistent object narratives represented by compact object-state tokens. Rather than compressing frame-wise features before establishing temporal correspondence, SlotNarrative first groups visual features into object-like slots and then associates recurring observations with clip-level object entries through a lightweight, parameter-free memory that integrates multiple complementary matching cues. Each retained entry is serialized into two token types: an identity token that summarizes persistent object appearance and a set of state tokens that encode segment-level appearance, geometry, visibility, and trajectory information. This design yields an interface of only 144 allocated visual-token positions for a frozen Video-LLM, independent of the number of sampled frames. Across multiple datasets, SlotNarrative achieves a favorable trade-off between accuracy and visual-token count compared with prior compact Video-LLM interfaces. Experimental results establish persistent object narratives as a compact, structured, and temporally organized visual interface for Video-LLMs. Our code will be made publicly available.

Junzhe Chen, Siyuan Meng, Xiaojie Guo

Tianjin University

Visual Tokenization Video-Language Models Video Representation Learning Visual Token Compression Temporal Video Understanding

Aug 5, 2026cs.CV

SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding

Surgical procedures unfold as structured and recurring clinical events, whose real-time understanding via intraoperative surgical videos is critical for intraoperative decision-making and support. However, existing video understanding methods force a trade-off: autoregressive video-language models support comprehensive reasoning but are not practical for time-sensitive clinical applications, whereas contrastive models offer low latency but struggle with complex scene understanding. Recently, generative retrieval has been explored for general-domain video understanding, but transferring it to surgery is not trivial because near-identical visual appearances may indicate semantically distinct events, and the terminology involved is highly surgery-specific. To this end, we propose SurgNarrator, a new generative retrieval framework tailored for surgical video understanding. We construct a well-curated surgery-centric vocabulary from surgical captions to define a clinically meaningful retrieval space. We then adapt the pre-trained Qwen3-VL-Embedding-8B to learn discriminative clinical representations with a temporally-aware contrastive objective. During inference, a hierarchical, procedure-aware retrieval strategy narrows the search space to the relevant procedure type, delivering fast and effective responses. Our method is comprehensively evaluated on twelve benchmarks in a zero-shot setting and achieves consistent performance gains over state-of-the-art baselines, while reducing output-stage latency by more than two orders of magnitude compared with the generative baseline.

Yuqing Feng, Jiawei Ma, Kevin Qinghong Lin +6

Department of Computer Science, University of Liverpool, Liverpool L69 3BX, U.K. · Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China · Department of Engineering, University of Oxford, Oxford OX1 3PJ, U.K. +2

Surgical Video Understanding Generative Retrieval Visual Search Temporal Video Understanding

Aug 5, 2026cs.CV

TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognition

Understanding complex surgical scenes requires recognizing multiple interdependent entities, such as instruments, actions, and targets, while maintaining their relational consistency across time. Existing surgical triplet recognition methods struggle to jointly model intra-frame label dependencies and inter-frame temporal semantics in a unified manner. To address these limitations, we propose a unified framework that integrates spatial, relational, and temporal cues for robust surgical triplet recognition. Specifically, class-specific spatial priors are first extracted through a multi-scale encoder. These priors are then refined by a Label Correlation Modeling module with multi-scale class activation map-guided relational extraction (MS-CAMRE), enabling the model to capture both static co-occurrence patterns and dynamic contextual dependencies among triplet components. Furthermore, a Bidirectional Temporal-Relational Fusion Attention (BTRFA) module harmonizes temporal and relational representations to achieve coherent temporal reasoning. We also introduce a new evaluation metric, the Triplet Consistency Error Rate (TCER), which quantitatively measures the model's ability to preserve causal and semantic consistency across triplets. Extensive experiments on the CholecT45 and ProstaTD datasets show that our method achieves state-of-the-art performance, improving AP_IVT by 5.1 percent and 7.8 percent, respectively. Moreover, according to TCER, our approach achieves relative reductions of more than 36 percent and 25 percent on the two datasets, respectively, demonstrating the effectiveness of our framework in temporal-relational co-reasoning.

Fang Li, Shihao Zou, Weixin Si +3

State Key Laboratory of Virtual Reality Technology and Systems, Beihang University · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology

Surgical Video Understanding Relational Deep Learning Temporal Attention Temporal Video Understanding

Aug 5, 2026cs.CV

REZE: Recognition-Based Zero-Shot Extraction for Video Temporal Grounding

Video temporal grounding (VTG) refers to the task of identifying the time interval in a video that corresponds to a given natural-language query. A common zero-shot strategy asks a large vision-language model (VLM) to generate the start and end timestamps directly, so the result depends heavily on the design and training of the model, and grounding accuracy differs widely from one VLM to another. We therefore propose REcognition-based Zero-shot Extraction (REZE), a simple training-free method that splits the video into short clips, asks the model for a clip-level confidence score for the query, and uses a deterministic algorithm to convert the resulting score curve into the output required by the task. Because temporal aggregation is performed outside the model, REZE adapts to different task outputs, from single- and multi-interval moment retrieval to highlight detection. On QVHighlights, REZE improves the best reported training-free moment-retrieval mAP from 38.23 to 40.32, while on highlight detection it reaches 44.18 mAP and 73.41 HIT@1, establishing a new state of the art among training-free methods. Its HIT@1 also outperforms all fully supervised SoTAs on the QVHighlights test split. We evaluate REZE on seven backbones from three model families. On Charades-STA and QVHighlights, it outperforms direct timestamp generation in every available comparison. We further observe that with REZE an earlier-generation model can approach the native performance of a newer model in its family.

Boyang Li, Chenhui Gou, Jianfei Cai

Department of Data Science and AI, Monash University

Temporal Video Grounding Zero-Shot Learning Temporal Video Understanding

Aug 5, 2026cs.CV

Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes

We introduce Predictive State Retrieval (PSR), a task in which a model observes a short video prefix and a temporal question about an object's future state, then retrieves instances from other videos or images that depict that state. Unlike action anticipation, which predicts a label, moment retrieval, which localizes an observed event within a video, or video generation, which synthesizes pixels, PSR combines anticipation with cross-instance retrieval across multiple temporal horizons. We construct a benchmark from four datasets with graded, human-validated ground truth, difficulty tiers, and an oracle ceiling. We also propose LFTR, a lightweight retriever with frozen encoders that predicts a question- and horizon-conditioned future latent and matches it in complementary semantic and visual spaces. A ceiling decomposition reveals a clear bottleneck: the true future state is highly retrievable once specified, whereas every predictor we evaluate, including a large multimodal language model with access to the prefix frames, remains far below the oracle. Thus, forecasting rather than perception is the central learnable challenge. LFTR narrows this gap at substantially lower inference cost, and ablations attribute its gains to cross-space fusion and hard-negative training rather than latent rollout. We release the benchmark, code, and evaluation scripts.

Quynh Vo, Thong Nguyen, Vinh-Hien Do +2

Centre for AI Research, VinUniversity · National University of Singapore

Cross-Modal Retrieval Video Prediction Predictive Representation Learning Video Retrieval Temporal Video Understanding

Aug 4, 2026cs.CV

AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding

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.

Yuxiang Duan, Huining Li, Ao Li +6

C-FAIR & School of software, Shandong University · Renmin University of China · Nanjing Agricultural University +1

Multi-Agent Systems Video Anomaly Detection Temporal Video Understanding

Aug 4, 2026cs.SD

Multi-Task Multi-Frame Visual Piano Transcription

Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist long after key release, so audio systems predict pedal-extended offsets rather than physical key release. Yet existing Visual Piano Transcription (VPT) systems focus on onset detection from short video windows, offset accuracy lags onset by a wide margin, and note-level velocity has not been reported. To address these gaps, we present V2N (Video to Notes), the first complete VPT system: a shared temporal backbone feeds task-specific heads for onset, offset, key hold, and velocity, jointly trained with per-frame supervision rather than only at the window center. Ablations show that multi-task supervision enables offset and velocity prediction while improving onset accuracy; longer temporal context yields further improvements. V2N sets new state-of-the-art results on PianoVAM and R3.

Yonghyun Kim, Hoyeol Sohn, Juhan Nam +1

Music Informatics Group, Georgia Institute of Technology, USA · Graduate School of Culture Technology, KAIST, South Korea

Automatic Music Transcription Temporal Video Understanding

Aug 4, 2026cs.MM

Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models

When asked which of two events came first, video large language models can fail in two opposite ways: cave to a false claim, or reject a true one. Prior video sycophancy work measures only the first and mitigates it by teaching the model to trust the user less, a fix known in text and image models to worsen the second. In video, both failures come from two causes the literature treats as one: availability, whether the sparse sampled frames contain the two events, and weighting, whether that evidence is trusted over the user. We separate them with two interventions that keep the claim fixed: a frame-preserving reorder that flips the claim's truth, and a sampling-offset shift that captures or misses both events at a fixed frame budget. When the events are missed, the two twins present identical frames, so each of the nine models we evaluate accepts a true and a false claim at the same rate, making Youden's

J=0

by construction. Availability is necessary but not sufficient. Five of the nine read the order, yet four of those five still cave to the false claim, so their deference hits a weighting ceiling. Since trust cannot be calibrated over evidence that was never sampled, we propose a reversal test that cancels the model's order prior by scoring the sampled frames forward and reversed, then answers, resamples, or abstains without reading the claim. The test raises the order accuracy to 0.92-1.00 on the models that read the order and abstains rather than guesses on those that cannot.

Yuxin Cao, Wei Song, Jingling Xue +1

National University of Singapore, Singapore · University of New South Wales, Australia

Selective Prediction Video-Language Model Evaluation Video Frame Selection Temporal Video Understanding

Aug 3, 2026cs.CV

Event ActivityNet: A Large-Scale Simulated-Event Benchmark for Untrimmed Action Understanding

Long-horizon event-based action understanding remains underexplored because existing datasets largely comprise short, trimmed clips, while collecting native event streams with dense temporal annotations is costly. We introduce Event ActivityNet, a large-scale simulated-event benchmark derived from human-annotated, untrimmed ActivityNet videos. It comprises 3,263 videos, 200 action classes, and 106.94 hours, with matched 5-bin and 9-bin event-voxel representations, temporal action annotations, and timestamped captions. The benchmark supports annotated-segment action recognition, auxiliary event-language alignment, and causal online temporal action localization. We generate event voxels directly from non-interpolated source videos in decoded frame order, retain per-video rational nominal or average frame-rate metadata for approximate time mapping, and use action-center reconstruction LPIPS as a soft diagnostic of retained reconstructable content. We establish baselines for adaptive event framing, prompt-caption alignment, and event-only, RGB-only, and RGB-event localization. Under a progressive nested-scale training protocol, recognition Top-1 accuracy increases from 52.25 to 66.42, while online temporal localization average mAP improves from 21.7 to 29.0. Moreover, staged Event ActivityNet pretraining followed by native-event fine-tuning consistently outperforms target-only and joint-from-scratch training across multiple supervision budgets. Event ActivityNet provides a scalable benchmark for long-horizon event modeling, although native-camera evaluation remains essential for deployment-oriented conclusions.

Cheng-Yao Hong, Ting-Wei Lin, Yun-Chung Lai +3

Institute of Information Science, Academia Sinica, Taiwan · Department of Computer Science, National Tsing Hua University, Taiwan

Event-Based Vision Video Action Recognition Temporal Action Detection Temporal Video Understanding Temporal Action Localization

Jul 30, 2026cs.CV

VisualRouter: Query-Grounded Visual Sampling for Long Video Understanding

Large vision-language models (LVLMs) have achieved significant progress in video understanding, yet understanding long videos remains challenging due to the large number of visual tokens and limited context windows. Visual sampling provides a practical solution by selecting an informative subset of frames. However, existing methods typically either rely on relevance-aware sampling, leading to redundant frame selection and insufficient temporal coverage, or adopt a fixed sampling strategy regardless of query type. In this paper, we propose VisualRouter, a training-free and plug-and-play framework for query-grounded visual sampling. VisualRouter first classifies each query as either global or local and then applies the corresponding sampling strategy. For global queries, it employs a relevance-coverage hybrid strategy that preserves temporal coverage while retaining query-relevant visual evidence. For local queries, it adopts an event-aware frame selection strategy that performs event partitioning, segment-level frame allocation, and intra-event frame selection, jointly balancing relevance, coverage, and diversity with a limited number of input frames. Experiments show that VisualRouter consistently improves multiple LVLMs over uniform sampling, achieving gains of 5.2%, 7.7%, and 11.6% on Video-MME, LongVideoBench, and MLVU with Qwen2.5-VL-7B, and outperforming existing training-free visual sampling methods under the same setting.

Haiyue Zhang, Yi Bin, Xun Jiang +5

Tongji University, Shanghai, China · University of Electronic Science and Technology of China, Chengdu, China

Large Vision-Language Models Long-Video Understanding Temporal Video Understanding Query-Aware Video Frame Selection

Jul 30, 2026cs.AI

HyperClaim: Fine-Grained Cross-Modal Hypergraph Reasoning for Video Misinformation Detection

Video misinformation detection is often approached through global multimodal fusion or free-form multimodal reasoning. Both paradigms can under-represent localized authenticity cues that arise from coupled interactions among query phrases, contextual text, and short temporal spans of frames. Because such interactions are inherently higher-order, pairwise graph formulations are insufficient to capture multi-way cross-modal dependencies, whereas hypergraphs offer a suitable representation for these relations. We propose HyperClaim, a discriminative temporal hypergraph framework for sample-level authenticity classification. Using the title or benchmark-provided paired text as a claim-like query, HyperClaim constructs a sparse heterogeneous hypergraph over query tokens, evidence tokens, and sampled frames; applies confidence-aware filtering and source budgeting to form compact text-frame and short-range temporal evidence units; performs adaptive soft-incidence reasoning with residual text-video calibration; and aggregates textual, visual, and hyperedge states through a discrepancy-aware readout. Without relying on generated rationales or external tool calls, HyperClaim preserves fine-grained cross-modal and temporal structure that global fusion tends to flatten. Under the FactGuard temporal protocol, it achieves 83.7%, 82.0%, and 87.3% accuracy on FakeSV, FakeTT, and FakeVV, respectively, outperforming strong discriminative and reasoning-centric baselines. Learned incidence and attention weights further reveal token- and frame-level structure.

Xiangbo Wang, Jiasheng Zhang, Xingtong Yu +2

School of Communication Engineering, Hangzhou Dianzi University · School of Computer Science and Technology, Xidian University · School of Computing and Information Systems, Singapore Management University +1

Fake News Detection Automated Fact-Checking Multimodal Graph Learning Hypergraph Learning Temporal Video Understanding

Jul 28, 2026cs.CV

Knowledge-Guided Multimodal Reasoning over Interacting Streams for Video-Level Ambivalence and Hesitancy Recognition

Ambivalence and hesitancy (A/H) are conflicting affective states that precede the delay or abandonment of health behaviour change. Recognition of A/H at the video level is difficult, since the signal arises from disagreement across and within facial, vocal, linguistic, and bodily modalities, and manifests differently across individuals. The proposed PRISM-AH (Predictive Reasoning over Interacting Streams for Multimodal Ambivalence/Hesitancy Recognition), is a framework that treats A/H as a multimodal conflict that unfolds over time. Frozen vision, audio, and text encoders are aligned into short time windows and passed to a lightweight streaming model that scores cross-modal dissonance, predicts each next window to expose a hesitation surprise signal, discovers behaviour prototypes, and is conditioned on participant metadata. Dense window-level annotations supervise the model as an auxiliary objective, and the decision threshold is calibrated for macro F1. A knowledge-guided large language model then reasons over structured evidence using the expert cue taxonomy of the dataset, and its verdict is fused late only when validation performance improves. On the labelled public test partition of 525 videos, PRISM-AH attains a macro F1 of 0.6133, compared to the reported zero-shot baseline of 0.2827. The reasoning gain is validated to transfer from validation to the larger test partition.

Podakanti Satyajith Chary, Barath Parthiban, Pranesh Velmurugan +2

Department of Engineering Science, IIT Hyderabad, India · Department of Biomedical Engineering, IIT Hyderabad, India

Multimodal Reasoning Multimodal Emotion Recognition Ambivalence and Hesitancy Recognition Affective Computing Temporal Video Understanding

Jul 28, 2026cs.CV

FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding

Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible. However, the density of relevant content decreases sharply as video sequence length increases, and exposing the model to more irrelevant content measurably reduces its accuracy. In this paper, we address the problem of maximizing query-relevant information in a frame subset selected at inference time, without training. FORGE (Frame Orthogonality in Relevance Geometry) is a model-agnostic method that induces a query-conditioned geometry on a pretrained multimodal embedding space, unifying relevance and diversity into a single objective. In this space, frames that cover independent query-relevant directions are far apart, and selecting the subset of maximum information captures diverse query-relevant content within the budget. Experiments on Video-MME and LongVideoBench at budgets of 16, 32, and 64 frames show that FORGE improves the unified keyframe selection score by 11.0-15.3 points over the strongest training-free baseline and up to doubles keyframe recall (0.415 vs. 0.204 at K=64 on Video-MME). The gains extend to question answering, where accuracy improves in every evaluated setting across eight open-source MLLMs spanning 4B to 32B parameters, by up to 8.7 points over uniform sampling and 5.2 points over the strongest baseline. Our findings suggest that aligning the embedding space with the query's high-dimensional structure is a promising direction for inference-time video understanding.

Ghazal Kaviani, Ghassan AlRegib

1OLIVES at the Center for Signal and Information Processing (CSIP), School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA.

Efficient Multimodal Inference Multimodal Large Language Models Multimodal Embedding Video Frame Selection Temporal Video Understanding Query-Aware Video Frame Selection

Jul 27, 2026cs.CV

LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos

Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. While recent keyframe sampling methods attempt to mitigate this by distilling video inputs into a compact set of query-relevant frames, navigating the vast spatio-temporal search space remains challenging, as spatial detail and temporal coverage often conflict. To address this, we introduce LENS, a training-free keyframe sampling framework that dynamically decides when to zoom in for fine-grained details and when to zoom out for broader context based on the text query. Concretely, LENS adaptively allocates a limited frame budget between spatial zoom-ins, which highlight query-relevant regions within individual frames, and temporal zoom-outs, which expand the temporal scope through multi-frame aggregation, enabling the model to reason across multiple granularities while capturing both high-fidelity details and long-range context. Across diverse long-form video benchmarks, LENS consistently outperforms prior state-of-the-art keyframe sampling methods and delivers substantial gains over uniform sampling, improving Video-MME accuracy from 53.3% to 60.7% with Qwen2.5-VL.Code is available at https://github.com/zhangce01/LENS.

Ce Zhang, Jinxi He, Katia Sycara +1

Robotics Institute, Carnegie Mellon University

Multimodal Large Language Models Long-Video Understanding Temporal Video Understanding Query-Aware Video Frame Selection

Jul 27, 2026cs.CV

MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning

Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality image-text pairs. However, the performance of VLMs often degrades in the video domain due to the essential need for temporal understanding and the scarcity of large-scale annotated video data. In this work, we focus on marine video understanding, which brings further challenges: first, it requires substantial domain expertise; and video VLMs usually struggle with localizing and interpreting critical information from marine videos, as the informative events are typically sparse, unpredictable, and unevenly distributed. To address these challenges, we carefully curate the first event-centric marine video understanding dataset called MarineEVT, which features 20K multi-task, video-level visual question-answering pairs spanning multiple dimensions of marine understanding and analysis. Meanwhile, based on MarineEVT, we decompose marine video understanding as an Event-centric Visual Tool-integrated Reasoning process EVT-R1 for short, where we leverage powerful visual tools to drive the model to localize and interpret critical information aligned with visual questions and human intent. To demonstrate its effectiveness, we compare EVT-R1 against 11 SOTA VLMs in different settings. EVT-R1 outperforms the top open-source and top commercial models by 5.22 and 11.09, respectively. MarineEVT and EVT-R1 lay the foundation for ecological discovery and marine education, fostering the development of VLMs capable of interpreting marine dynamics, reasoning about ecological interactions, and supporting sustainable ocean video understanding and analysis.

Tuan-An To, Yuk-Kwan Wong, Tuan-Anh Vu +2

The Hong Kong University of Science and Technology, Hong Kong, China · University of California, Los Angeles CA, USA · University of Electronic Science and Technology of China, China

Visual Question Answering Video Understanding Tool Use in VLMs VLM Reasoning Temporal Video Understanding

Jul 25, 2026cs.CV

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

Existing Large Vision-Language Models (LVLMs) struggle with long-form video understanding due to the quadratic computational cost of visual tokens. While recent efficient methods attempt to compress tokens via hard pruning or uniform merging, they operate strictly in the spatial feature domain, where robust structural context and discriminative semantic details are inherently entangled. In this work, we propose WaveZip, a joint signal-frequency-domain framework for efficient video inference. Driven by the insight that temporal redundancy resides in low-pass approximation scales while spatial saliency strongly correlates with high-frequency components, WaveZip leverages Discrete Wavelet Transforms (DWT) to disentangle these signals. Temporally, it employs 1D DWT to analyze query-frame relevance, and the resulting high-frequency coefficients are further gated by inter-frame differences, with both signals jointly driving the dynamic allocation of a precise frame-level token budget. Spatially, a 2D DWT decomposes features into low-frequency approximations and high-frequency detail components, where the high-frequency coefficients are modulated within query-salient regions to regulate spatial reconstruction. Importantly, WaveZip requires no task-specific training and can be seamlessly integrated into off-the-shelf LVLMs to boost inference efficiency. Extensive experiments on long video understanding benchmarks demonstrate that WaveZip retains 99.6% of the full performance under an extreme 10x compression ratio, consistently outperforming state-of-the-art methods.

Yuhui Zeng, Wang Chen, Jinfa Huang +5

Media Analytics and Computing Lab, Xiamen University, Xiamen, China · Department of Computer Science, University of Rochester, Rochester, NY, USA

Efficient VLM Inference Video Token Compression Visual Token Compression Temporal Video Understanding