Temporal Video Understanding

Ask about this topic

Overview

Temporal video understanding studies how actions and events unfold, how objects and states change, and how evidence across frames supports tasks such as action localization, moment retrieval, video question answering, and future prediction. Approaches include temporal transformers and state-space models, motion and trajectory representations, event graphs and memory, and adaptive frame or token selection; vision-language models are also trained or guided to reason over video evidence. Evaluation spans action-localization datasets, long-video question answering, temporal-order and counting tests, and streaming settings where models must decide when to respond. A central tension is that models can perform well on broad benchmarks while relying on static cues or language priors rather than temporal evidence, and efficient sampling or compression must retain the brief events needed for reliable reasoning.

Latest papers

CardsList

371 papers45 papers in the last four weeks, up 45% on the four weeks before. 0.3% of all new papers.

May 11, 2026

Stabilizing Temporal Inference Dynamics for Online Surgical Phase Recognition

Online Surgical Phase Recognition (SPR) models can reach high frame-wise accuracy, yet their predictions often lack temporal stability, fragmenting workflow understanding and reducing the reliability of downstream assistance. We show that this instability is not random noise but arises from two mechanisms: early misclassifications corrupt temporal feature states and propagate forward to form error cascades, and phase transitions follow evidence-accumulation dynamics whereas most online SPR systems rely on memoryless frame-wise decisions, making them sensitive to transient confidence fluctuations. We propose a unified Train-Inference-Evaluation framework that explicitly stabilizes temporal inference dynamics using model-agnostic, plug-and-play components. For training, the Temporal Error-Cascade (TEC) loss suppresses error onset and mitigates forward error propagation by stabilizing temporal feature evolution. For inference, the Evidence-Gated Transition Predictor (EGTP) enforces evidence-driven state transitions, allowing phase changes only when accumulated evidence exceeds a confidence boundary. For evaluation, we introduce the Temporal Fragmentation Index (TFI), a reliability-aware metric that quantifies instability-induced temporal disagreement beyond conventional frame-wise and token-based measures. Experiments on Cholec80 and AutoLaparo across three representative backbones show that the proposed framework substantially improves temporal stability and reduces prediction fragmentation, while maintaining or modestly improving frame-wise performance.

Yang Liu, Ning Zhu, Jingjing Peng +4

King’s College London, London, UK · University of Electronic Science and Technology of China, Chengdu, China · Mach Drive

Surgical Video UnderstandingTemporal ConsistencyTemporal Video Understanding
AskPDF
May 11, 2026

StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video

Proactive streaming video understanding requires models to continuously process video streams and decide when to respond, rather than merely what to respond. This naturally introduces a decision-making problem under partial observations, where models must balance early prediction against sufficient evidence. However, existing benchmarks largely follow a "see-then-answer" paradigm, where responses are triggered only after explicit evidence appears, effectively reducing proactive reasoning to delayed perception. As a result, they fail to evaluate a model's ability to make timely and reliable decisions under incomplete observations. Moreover, training proactive models is inherently challenging due to the extreme imbalance between silence and response signals in streaming trajectories, as well as the need to jointly optimize response correctness and timing. To address these challenges, we introduce StreamPro-Bench, a new benchmark that evaluates streaming models from three complementary perspectives: Perception Understanding, Temporal Reasoning, and Proactive Agency, where the last measures a model's ability to make early yet reliable decisions under partial observations. We further propose StreamPro, a two-stage training framework for proactive learning. First, we introduce CB-Stream Loss to mitigate the severe supervision imbalance during supervised fine-tuning (SFT). Then, we apply Group Relative Policy Optimization (GRPO) with a multi-grained reward design that involves both turn-level and trajectory-level rewards. Experiments show that StreamPro significantly improves proactive performance. On StreamPro-Bench, it achieves 41.5, substantially outperforming the previous best (10.4), while also maintaining strong performance on real-time streaming benchmarks, achieving 78.9 on StreamingBench-RTVU.

Ao Li, Zihan Xiao, Zihao Yue +7

1AIM3 Lab, Renmin University of China · 2MiLM Plus, Xiaomi Inc. · 3Peking University

Streaming Video UnderstandingTemporal Video Understanding
AskPDF
May 11, 2026

OZ-TAL: Online Zero-Shot Temporal Action Localization

Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon their completion. Recent advancements in this field focus on developing more sophisticated frameworks, shifting from Online Action Detection (OAD)-based aggregation paradigm to instance-level understanding. However, existing approaches are typically trained on specific domains and often exhibit limited generalization capabilities when applied to arbitrary videos, particularly in the presence of previously unseen actions. In this paper, we introduce a new task called Online Zero-shot Temporal Action Localization (OZ-TAL), which aims to detect previously unseen actions in an online fashion. Furthermore, we propose a training-free framework that leverages off-the-shelf Vision-Language Models (VLMs) while introducing additional mechanisms to enhance visual representations and mitigate their inherent biases. We establish new benchmarks and representative baselines for OZ-TAL on THUMOS14 and ActivityNet-1.3, and extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches under both offline and online zero-shot settings.

Chaolei Han, Hongsong Wang, Xin Gong +1

School of Cyber Science and Engineering, Southeast University, Nanjing 211102, China · Engineering Research Center of Blockchain Application, Supervision and Management (Southeast University), Ministry of Education; Purple Mountain Laboratories, Nanjing 211111, China · School of Computer Science and Engineering, Southeast University, Nanjing 211102, China

Zero-Shot LearningTemporal Action DetectionTemporal Video Understanding
AskPDF
May 11, 2026

TOC-Bench: A Temporal Object Consistency Benchmark for Video Large Language Models

Video large language models (Video-LLMs) have made strong progress in general video understanding, but their ability to maintain temporal object consistency remains underexplored. Existing benchmarks often emphasize event recognition, action understanding, or coarse temporal reasoning, while rarely testing whether models can preserve the identity, state, and continuity of the same object across occlusion, disappearance, reappearance, state transitions, and cross-object interactions. We introduce TOC-Bench, a diagnostic benchmark for evaluating temporal object consistency in Video-LLMs. TOC-Bench is object-track grounded: each queried subject is linked to a per-frame trajectory and a structured temporal event timeline. To ensure that questions require temporally ordered visual evidence rather than language priors, single-frame shortcuts, or unordered frame cues, we design a three-layer temporal-necessity filtering protocol, which removes 60.7% of candidate QA pairs and retains 17,900 temporally dependent items across 10 diagnostic dimensions. From this pool, we construct a human-verified benchmark with 2,323 high-quality QA pairs over 1,951 videos. Experiments on representative Video-LLMs show that temporal object consistency remains a major unsolved challenge, with notable weaknesses in event counting, event ordering, identity-sensitive reasoning, and hallucination-aware verification, even when models perform well on general video understanding benchmarks. These results suggest that object-centric temporal coherence is a key bottleneck for current Video-LLMs, and that TOC-Bench provides a focused platform for diagnosing and improving object-aware temporal reasoning. The resource is available at https://github.com/cjzcjz666/toc_bench.git.

Junzhe Chen, Siyuan Meng, Yuxi Chen +3

Tianjin University

Video-Language Model EvaluationVideo-Language ModelsMultimodal Model EvaluationTemporal Video Understanding
AskPDF
May 10, 2026

Fetal Brain Imaging: A Composite Neural Network Approach for Keyframe Detection in Ultrasound Videos

This article presents a novel approach to keyframe detection in ultrasound videos, with a particular focus on fetal brain imaging. The proposed model is a composite neural network architecture that combines a Convolutional Neural Network (CNN) with a Recurrent Neural Network (RNN). The CNN extracts spatial features from individual video frames, while the RNN captures temporal dependencies between consecutive frames within each video sequence. The proposed model may improve the efficiency and accuracy of fetal brain ultrasound analysis, thereby supporting earlier detection, diagnosis, and treatment planning for selected fetal brain conditions.

Aleksander Zamojski, Kacper Jarczak, Radoslaw Roszczyk

Warsaw Universitu of Technology Warsaw, Poland · Warsaw University of Technology Warsaw, Poland

Fetal MRIUltrasound ImagingVideo Frame SelectionNeuroimagingTemporal Video Understanding
AskPDF
May 10, 2026

SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy

Vision-language models (VLMs) have recently shown strong potential in soccer video understanding. However, given the high complexity of soccer videos due to large viewpoint variations, rapid shot transitions, and cluttered scenes, it remains unclear on whether VLMs rely on meaningful visual evidence or exploit spurious correlations and shortcut learning. Existing evaluation protocols focus primarily on classification accuracy and do not assess visual grounding. To address this limitation, we introduce SoccerLens, a benchmark for grounded soccer video understanding. The benchmark contains annotated video segments spanning 1313 common soccer events, with structured visual cues organized into three levels of semantic relevance. We further extend the attribution method of Chefer [arXiv:2103.15679] to jointly model spatial and temporal attention, and introduce evaluation metrics that measure whether model attention aligns with annotated cues or drifts toward spurious regions. Our evaluation of state-of-the-art soccer VLMs shows that, despite strong classification accuracy, current models fail to exceed 50%50\% grounding performance even under the loosest cue definitions and consistently underutilize temporal information. These results reveal a substantial gap between predictive performance and true visual grounding, highlighting the need for grounded evaluation in complex spatio-temporal domains such as soccer.

Ismael Elsharkawi, Ahmed Sait, Silvio Giancola +3

Department of Computer Science and Engineering, The American University in Cairo · Image And Visual Understanding Lab (IVUL), KAUST

VLM EvaluationSports Video AnalysisVisual GroundingShortcut LearningTemporal Video Understanding
AskPDF
May 10, 2026

Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs

Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling. We propose Fre-Res, a budget-adaptive dual-track video-token compression framework that separates these two forms of evidence. Fre-Res preserves sparse high-fidelity spatial anchors and represents dense temporal evolution through compact residual-frequency tokens. Specifically, it applies temporal 1D-DCT to inter-frame residual trajectories in vision-latent space, where we observe strong low-frequency concentration. To align frequency-domain dynamics with native visual embeddings, Fre-Res introduces a Spatial-Guided Absorber that injects temporal residual information into spatially corresponding anchor tokens. Across fine-grained short-video and long-video reasoning benchmarks, Fre-Res achieves a favorable accuracy--efficiency trade-off, matching or approaching full-token performance while substantially reducing visual-token length. Extensive ablations further show that temporal-frequency residuals preserve causal transition cues, while spatial anchors remain essential for fine-grained object and layout reasoning.

Yigui Feng, Qinglin Wang, Yang Liu +1

The College of Computer Science, National University of Defense Technology, Changsha, Hunan, China · College of Computer Science, National University of Defense Technology, Deya Road 109, Changsha, Hunan 410073, China · The Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, Guangdong, China +1

Efficient VLM InferenceVisual TokenizationVideo Token CompressionVisual Token CompressionTemporal Video Understanding
AskPDF
May 9, 2026

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models

While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We argue this stems from a failure in spatio-temporal monitoring, the ability to persistently track object identities, states, and relations over time. Existing benchmarks obscure this deficit by relying on single final-answer evaluations for queries that can often be resolved via local visual cues or statistical priors. To rigorously diagnose this, we introduce STEMO-Bench (Spatio-TEmporal MOnitoring), a benchmark of human-verified object-centric facts that evaluates intermediate reasoning by decomposing queries into sub-questions, distinguishing genuine temporal understanding from coincidental correctness. To address failure modes exposed by STEMO, we propose STEMO-Track, a novel object-centric framework that explicitly constructs and reasons over structured object trajectories via chunk-wise state extraction and temporal aggregation. Extensive experiments demonstrate that our object-centric framework significantly reduces hallucinated answers and improves spatio-temporal reasoning consistency over state-of-the-art MLLMs.

Tri Cao, Khoi Le, Thong Nguyen +7

National University of Singapore · VinUniversity · Nanyang Technological University

VLM EvaluationObject Hallucination in VLMsMultimodal Large Language ModelsTemporal Video Understanding
AskPDF
May 9, 2026

MLCR: Multi-Level Cue Refinement for Long-Term Multimodal Action Quality Assessment

Long-term multimodal action quality assessment (AQA) evaluates action execution in several-minute audiovisual sequences by mining discriminative quality cues for score prediction. Existing multimodal methods usually model entire sequences with a single temporal encoder and fuse modality features by direct alignment or concatenation, causing key cues to be obscured by global trends, weakened by modal redundancy, and distorted during one-shot score mapping. To address this issue, we reformulate long-term multimodal AQA as a quality cue organization problem and propose MLCR, a multi-level cue refinement framework. MLCR organizes quality evidence at three levels: intra-modal representation, cross-modal interaction, and stage-wise aggregation. Specifically, the intra-modal decoupling encoder (IMDE) preserves modality identity while refining global temporal context and local frequency details. The cross-modal dynamic complementarity-aware retrieval (CMDCR) module retrieves incremental evidence conditioned on the evolving fused state and suppresses redundant responses. The stage-wise multimodal integration (SMI) block progressively accumulates intra-modal and cross-modal cues to refine the fused representation. Experiments on the Rhythmic Gymnastics and Fis-V datasets show that MLCR achieves the best or second-best performance in both Spearman correlation and prediction error, demonstrating its effectiveness and robustness.

Qiqi Li, Pengfei Wang, Hongyu Chen +1

Qiushi Academy for Advanced Studies (QAAS), Zhejiang University, Hangzhou, Zhejiang, 310007, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, 310007, China · School of Software Technology, Zhejiang University, Hangzhou, Zhejiang, 310007, China +3

Multimodal FusionAction Quality AssessmentTemporal Video Understanding
AskPDF
May 8, 2026

TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos

Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams, whereas existing benchmarks largely fail to evaluate this capability. They restrict videos to short clips, isolate modalities, or reduce questions to one-hop perception. We introduce TraceAV-Bench, the first benchmark to jointly evaluate multi-hop reasoning over long audio-visual trajectories and multimodal hallucination robustness. TraceAV-Bench comprises 2,200 rigorously validated multiple-choice questions over 578 long videos, totaling 339.5 hours, spanning 4 evaluation dimensions and 15 sub-tasks. Each question is grounded in an explicit reasoning chain that averages 3.68 hops across a 15.1-minute temporal span. The dataset is built by a three-step semi-automated pipeline followed by a strict quality assurance process. Evaluation of multiple representative OmniLLMs on TraceAV-Bench reveals that the benchmark poses a persistent challenge across all models, with the strongest closed-source model (Gemini 3.1 Pro) reaching only 68.29% on general tasks, and the best open-source model (Ming-Flash-Omni-2.0) reaching 51.70%, leaving substantial headroom. Moreover, we find that robustness to multimodal hallucination is largely decoupled from general multimodal reasoning performance. We anticipate that TraceAV-Bench will stimulate further research toward OmniLLMs that can reason coherently and faithfully over long-form audio-visual content.

Hengyi Feng, Hao Liang, Mingrui Chen +6

University of Electronic Science and Technology of China · Peking University · Zhongguancun Academy +1

Audio-Visual UnderstandingMultimodal HallucinationAudio-Visual QAMultimodal Model EvaluationTemporal Video UnderstandingMultimodal Understanding
AskPDF
May 8, 2026

Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs

The Arrow-of-Time (AoT) task, determining whether a video plays forward or backward by recognizing temporal irreversibility, is one humans solve with near-perfect accuracy, yet frontier Video Large Language Models (Video-LLMs) perform only modestly above chance. This gap raises a key question: do visual backbones fail to encode temporal information, or does information bottleneck lie elsewhere in the Video-LLM architecture? We address this question by isolating the vision encoder from the Video-LLM and tracing temporal information across the encoder, projector, and LLM. We find that video-centric encoders with explicit temporal modeling encode strong temporal signals, whereas frame-centric encoders do not. However, when video-centric representations are passed through a standard Video-LLM architecture, performance often collapses, revealing a bottleneck of temporal information flow. We identify projector design as a key factor: Q-Former disrupts temporal information, while a time-preserved MLP projection substantially improves the LLM's access to such information. Our layer-wise analysis further shows temporal representation dynamics across encoder layers. Guided by these findings, we build a Video-LLM with temporal-aware video-centric encoder, time-preserved projector, and AoT supervision, surpassing human performance on AoTPPB_{PPB} with 98.1% accuracy, and improving broader temporal reasoning tasks by up to 6.0 points on VITATECS-Direction and 1.3 points on TVBench. Our results show that temporal reasoning in Video-LLMs requires both effective temporal encoding and reliable transfer of this information to the LLM.

Peitao Han, Fei Cheng, Lis K. Pereira +2

The University of Osaka · Center for Information and Neural Networks · National Institute of Information and Communications Technology +2

Video-Language ModelsTemporal Reasoning in Language ModelsVideo ReasoningTemporal Video UnderstandingVision-Language ModelsTemporal Reasoning in VLMs+1
AskPDF
May 7, 2026

Jointly Learning Structured Representations and Stabilized Affinity for Human Motion Segmentation

Human Motion Segmentation (HMS), which aims to partition a video into non-overlapping segments corresponding to different human motions, has recently attracted increasing research attention. Existing HMS approaches are predominantly based on subspace clustering, which are grounded on the assumption that the distribution of high-dimensional temporal features well aligns with a Union-of-Subspaces (UoS). For videos in the real world, however, the raw frame-level features often violate the UoS assumption and yield unsatisfactory segmentation performance. To address this issue, we propose an efficient and effective approach for HMS, named Temporal Deep Self-expressive subspace Clustering (TDSC), which jointly learns temporally consistent structured representations and stabilized affinity for accurate and robust HMS. Specifically, in TDSC, we alternately learn structured representations of the input frame features and self-expressive coefficients via a properly regularized self-expressive model, in which a coding-rate maximization regularizer is incorporated to avoid representation collapse and conform the learned representations to span a desired UoS distribution, and meanwhile, temporal constraints are incorporated to promote temporally adjacent frames to be partitioned into the same groups. Moreover, we develop a temporal momentum averaging mechanism to stabilize affinity evolution and design a reparameterization strategy to enable efficient optimization. We conduct extensive experiments on five benchmark HMS datasets using both conventional (HoG) and up-to-date deep features (i.e., CLIP, DINOv2) to validate the effectiveness of our approach.

Xianghan Meng, Zhiyuan Huang, Zhengyu Tong +1

School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, P.R. China

Representation LearningClusteringTemporal Video Understanding
AskPDF
May 6, 2026

Hybrid Congestion Classification Framework Using Flow-Guided Attention and Empirical Mode Decomposition

Accurate traffic congestion classification requires models that jointly capture roadway scene context and non-stationary traffic motion, yet most prior work treats these requirements in isolation. Vision-based methods often depend on appearance cues with standard temporal pooling, which can bias predictions toward static infrastructure, whereas signal-based approaches characterize temporal dynamics but lack the spatial context needed for scene-level localization. These complementary limitations motivate a unified framework that links motion evidence to spatial feature selection while preserving data-adaptive temporal characterization. This study therefore proposes FLO-EMD, a hybrid approach that couples motion-guided attention with empirical, data-driven temporal decomposition. Dense optical flow guides channel and spatial attention so that RGB features are refined toward motion-relevant regions. In parallel, aggregated flow statistics form compact motion traces that are decomposed using Empirical Mode Decomposition (EMD) to extract intrinsic temporal components. The resulting EMD embedding is fused with learned spatiotemporal representations to classify light, medium, and heavy congestion. Experiments on 1,050 five-second clips from four surveillance networks show that FLO-EMD achieves 97.5% overall test accuracy (weighted F1 = 0.9742), outperforming established baselines and remaining robust across diverse environmental conditions; ablation and sensitivity analyses further quantify the contributions of EMD, the number of intrinsic mode functions, and the selected motion descriptors.

Eugene Kofi Okrah Denteh, Blessing Agyei Kyem, Joshua Kofi Asamoah +1

Civil, Construction and Environmental Engineering Department, North Dakota State University, North Dakota, United States of America

Intelligent Transportation SystemsMultimodal FusionTemporal Video Understanding
AskPDF
May 4, 2026

TemPose-TF-ASF: Two-Stage Bidirectional Stroke Context Fusion for Badminton Stroke Classification

Accurate badminton stroke prediction is crucial for fine-grained sports analysis and tactical decision support. However, existing methods struggle to model rich temporal context. This paper introduces TemPose-TF-ASF (Adjacent-Stroke Fusion), a context-aware extension of TemPose. It enhances stroke recognition by incorporating stroke-type information from both preceding and subsequent strokes. A two-stage training and inference strategy is adopted. Preliminary predictions from the baseline model are reused as estimated temporal context. These predictions guide the joint optimization of the ASF module and the classifier. By explicitly modeling bidirectional temporal stroke dependencies, the proposed method can be seamlessly integrated into existing state-of-the-art models. Experiments on a large-scale badminton match dataset show consistent improvements over the baseline and its variants in terms of Accuracy and Macro-F1. Moreover, integrating ASF into other advanced methods yields notable performance gains. These results demonstrate strong transferability and generalization capability.

Tzu-Yu Liu, Duan-Shin Lee

Institute of Communications Engineering National Tsing Hua University, Hsinchu City, Taiwan · Department of Computer Science National Tsing Hua University, Hsinchu City, Taiwan

Sports Video AnalysisVideo Action RecognitionTemporal Action DetectionSequence ModelingTemporal Video Understanding
AskPDF
May 3, 2026

Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models

Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting frames effectively and efficiently, as standard uniform sampling is expensive and performance may plateau. Inspired by active perception theory, which posits that models gain information by acquiring data that differs from their expectations, we introduce Video Active Perception (VAP), a training-free method to enhance long-form video QA using VLMs. Our approach treats keyframe selection as data acquisition in active perception and leverages a lightweight text-conditioned video generation model to represent prior world knowledge. Empirically, VAP achieves state-of-the-art zero-shot results on long-form or reasoning video QA datasets such as EgoSchema, NExT-QA, ActivityNet-QA, IntentQA, and CLEVRER, achieving an increase of up to 5.6 x frame efficiency by frames per question over standard GPT-4o, Gemini 1.5 Pro, and LLaVA-OV. Moreover, VAP shows stronger reasoning abilities than previous methods and effectively selects keyframes relevant to questions. These findings highlight the potential of leveraging active perception to improve the frame effectiveness and efficiency of long-form video QA.

Martin Q. Ma, Willis Guo, Aditya Agrawal +4

Carnegie Mellon University · MIT

Active PerceptionEfficient VLM InferenceVideo QAVLM ReasoningTemporal Video UnderstandingQuery-Aware Video Frame Selection
AskPDF
May 2, 2026

VISTA: Video Interaction Spatio-Temporal Analysis Benchmark

Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity types, failing to capture the freeform, multi-action interactions between diverse entities which characterize real-world video understanding. Furthermore, the lack of a systematic framework for analyzing model failures across complementary spatio-temporal axes hinders comprehensive evaluation. To address these gaps, we introduce VISTA, a Video Interaction Spatio-Temporal Analysis benchmark designed for open-set, multi-entity and multi-action spatio-temporal understanding in VLMs. VISTA decomposes videos into interpretable entities, their associated actions, and relational dynamics, enabling multi-axis diagnostics and unified assessment of relational, spatial, and temporal understanding. Our benchmark integrates multiple datasets into a single interaction-aware taxonomy and comprises ~12K curated video-query pairs spanning diverse scenes and complexities. We systematically evaluate 11 state-of-the-art VLMs on VISTA, and break down aggregate performance across our taxonomy to reveal shortcomings and pronounced spatio-temporal biases obscured by traditional metrics. By providing detailed, taxonomy-driven diagnostics on a challenging dataset, VISTA offers a nuanced framework to guide advances in model design, pretraining strategies, and evaluation protocols. Overall, VISTA is the first, large-scale, interaction-aware diagnostic benchmark for spatio-temporal understanding in VLMs.

Alejandro Aparcedo, Akash Kumar, Aaryan Garg +5

University of Central Florida · BITS Pilani · Ho Chi Minh City University of Science +1

VLM EvaluationVideo UnderstandingTemporal Video Understanding
AskPDF
May 1, 2026

High-Speed Vision Improves Zero-Shot Semantic Understanding of Human Actions

Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar or hard-to-annotate actions is required. In scenarios such as rapid and less common activities, collecting sufficient labeled data for supervised learning is challenging, making zero-shot approaches a practical alternative for semantic understanding without task-specific training. While recent advances in large-scale pretrained models enable such zero-shot reasoning, the impact of temporal resolution, especially for rapid and fine-grained motions, remains underexplored. In this study, we investigate how temporal resolution affects zero-shot semantic understanding of high-speed human actions. Using kendo as a representative case of rapid and subtle motion patterns, we propose a training-free pipeline that combines a pre-trained video-language model for semantic representation with large language model-based reasoning for pairwise action comparison. Through controlled experiments across multiple frame rates (120 Hz, 60 Hz, and 30 Hz), we show that higher temporal resolution significantly improves semantic separability in zero-shot settings. We further analyze the role of tracking-based human joint information under both full and partial observation scenarios. Quantitative evaluation using a nearest-class prototype strategy demonstrates that high-speed video provides more stable and interpretable semantic representations for fast actions. These findings highlight the importance of temporal resolution in training-free action recognition and suggest that high-speed perception can enhance semantic understanding capabilities.

Yongpeng Cao, Yuji Yamakawa

Institute of Industrial Science, The University of Tokyo, Japan · Interfaculty Initiative in Information Studies, Graduate School of Interdisciplinary Information Studies, The University of Tokyo, Japan

Video UnderstandingZero-Shot LearningZero-Shot Action RecognitionVideo Action RecognitionTemporal Video Understanding
AskPDF
May 1, 2026

Scaling Video Understanding via Compact Latent Multi-Agent Collaboration

Multi-modal large language models (MLLMs) advance vision language understanding but face inherent limitations in long-video tasks due to bounded perception context budgets. Existing agentic methods mitigate this via rule-based preprocessing, yet often suffer from information loss, high cost, and reliance on textual intermediates. We propose MACF, an end-to-end Multi-Agent Collaboration Framework that decouples per-agent perception budgets from global video complexity, enabling scalable video understanding while preserving visual fidelity. MACF partitions videos into segments for locally budgeted agents and enables holistic reasoning via an agent-native latent communication protocol. Each agent encodes partial observations into compact, task-sufficient tokens in a shared embedding space, allowing efficient and information-preserving collaboration by a central coordinator. We introduce a curriculum training strategy that progressively enforces semantic alignment, evidence summarization, and cross-agent coordination. Extensive experiments on diverse video understanding benchmarks show that MACF consistently outperforms state-of-the-art MLLMs and multi-agent systems under identical budget constraints, demonstrating the effectiveness of our latent collaboration for scalable video understanding.

Kerui Chen, Jinglu Wang, Jianrong Zhang +3

Microsoft Research Asia · Zhejiang University · Guanming Lab.

Multi-Agent CollaborationLong-Video UnderstandingMulti-Agent CommunicationMulti-Agent LLMsTemporal Video Understanding
AskPDF
Apr 30, 2026

TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions

Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted video shots. We address this fundamental limitation by formalizing the Shot Transition Detection (STD) task. Rather than searching for ambiguous points, STD explicitly detects the continuous temporal segments of transitions. To tackle this, we propose TransVLM, a Vision-Language Model (VLM) framework for STD. Unlike regular VLMs that predominantly rely on spatial semantics and struggle with fine-grained inter-shot dynamics, our method explicitly injects optical flow as a critical motion prior at the input stage. Through a simple yet effective feature-fusion strategy, TransVLM directly processes concatenated color and motion representations, significantly enhancing its temporal awareness without incurring any additional visual token overhead on the language backbone. To overcome the severe class imbalance in public data, we design a scalable data engine to synthesize diverse transition videos for robust training, alongside a comprehensive benchmark for STD. Extensive experiments demonstrate that TransVLM achieves superior overall performance, outperforming traditional heuristic methods, specialized spatiotemporal networks, and top-tier VLMs. This work has been deployed to production. For more related research, please visit HeyGen Research (https://www.heygen.com/research) and HeyGen Avatar-V (https://www.heygen.com/research/avatar-v-model). Project page: https://chence17.github.io/TransVLM/

Ce Chen, Yi Ren, Yuanming Li +5

University of Melbourne · 2HeyGen Research · 3Nanyang Technological University

Vision-Language ModelsChange-Point DetectionTemporal Video Understanding
AskPDF
Apr 29, 2026

PKS4\text{PKS}^4:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding

Temporal modeling remains a fundamental challenge in video understanding, particularly as sequence lengths scale. Traditional video models relying on dense spatiotemporal attention suffer from quadratic computational costs for long videos. To circumvent these costs, recent approaches adapt image models for videos via Parameter-Efficient Fine-Tuning (PEFT) methods such as adapters. However, deeply inserting these modules incurs prohibitive activation memory overhead during back-propagation. While recent efficient State Space Models (SSMs) introduce linear complexity, they disrupt 2D spatial relationships and rely on extensive masked pre-training to recover spatial awareness. To overcome these limitations, we propose Parallel Kinematic Selective State Space Scanners (PKS4^4). We retain a standard 2D vision backbone for spatial semantics and insert a single plug-and-play PKS4^4 module with linear-complexity temporal scanning, avoiding temporal attention and multi-layer adapters. We first extract kinematic priors via a Kinematic Prior Encoder, which captures local displacements and motion boundaries through inter-frame correlations and differences. These priors drive linear-complexity SSMs to track underlying kinematic states, adaptively modulating update speeds and read-write strategies at each time step. Instead of global scanning, we deploy parallel scanners along the temporal dimension for each spatial location, preserving spatial structures while reducing overhead. Experiments on spatial-heavy and temporal-heavy action recognition benchmarks show that PKS4^4 achieves state-of-the-art performance. Remarkably, our method converges in merely 2020 epochs, achieving approximately 10×10\times lower training compute than pure video SSMs, establishing a new paradigm for efficient video understanding.

Lingjie Zeng, Hailun Zhang, Xiwen Wang +1

College of Computer Science, Sichuan University Chengdu, China

Visual SSMsVideo Action RecognitionTemporal Video Understanding
AskPDF
Apr 28, 2026

Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations

AI agents operating on user interfaces must understand how interfaces communicate state and feedback to act reliably. As a core communicative modality, animations are increasingly used in modern interfaces, serving critical functional purposes beyond mere aesthetics. Thus, understanding UI animation is essential for comprehensive interface interpretation. However, recent studies of Vision Language Models (VLMs) for UI understanding have focused primarily on static screenshots, leaving it unclear how well these models handle dynamic UI animations. To address this gap, we created AniMINT, a novel dataset of 300 densely annotated UI animation videos. We systematically evaluate state-of-the-art VLMs on UI animation understanding, including their abilities to perceive the animation effects, identify animation purposes, and interpret animation meaning. Our results show that VLMs can reliably detect primitive motion. However, their high-level animation interpretation remains inconsistent, with substantial gaps relative to human performance. Finally, we use Motion, Context, and Perceptual Cues (MCPC) to probe factors affecting VLM performance, revealing key bottlenecks and directions for future improvement.

Chen Liang, Xirui Jiang, Naihao Deng +2

University of Michigan

VLM EvaluationVideo UnderstandingTemporal Video Understanding
AskPDF
Apr 25, 2026

PushupBench: Your VLM is not good at counting pushups

Large vision-language models (VLMs) can recognize what happens in video but fail to count how many times. We introduce PushupBench, 446 long-form clips (avg. 36.7s) for evaluating repetition counting. The best frontier model achieves 42.1% exact accuracy; open-source 4B models score ∼\sim6%, matching supervised baselines. We show that accuracy alone misleads -- weaker models exploit the modal count rather than reason temporally. Fine-tuning on counting with 1k samples transfers to general video understanding: MVBench (+2.15), PerceptionTest (+1.88), TVBench (+4.54), suggesting counting is a proxy for broader temporal reasoning.PushupBench incorporated in lmms-eval (https://github.com/EvolvingLMMs-Lab/lmms-eval/pull/1262) and hosted on (pushupbench.com/)

Shengzhi Li, Jiarun Chen, Karun Sharma +2

Multimodal UnderstandingVideo-Language Model EvaluationLarge Vision-Language ModelsVLM EvaluationTemporal Video UnderstandingVideo Foundation Models+1
AskPDF
Apr 25, 2026

EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs

Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in applications such as social robots and human-computer interaction, where understanding human emotions is essential. However, existing benchmarks mainly formulate emotion understanding as a static recognition problem, leaving it largely unclear whether current MLLMs can understand emotion as a dynamic process that evolves, shifts between states, and unfolds across diverse social contexts. To bridge this gap, we present EmoTrans, a benchmark for evaluating emotion dynamics understanding in multimodal videos. EmoTrans contains 1,000 carefully collected and manually annotated video clips, covering 12 real-world scenarios, and further provides over 3,000 task-specific question-answer (QA) pairs for fine-grained evaluation. The benchmark introduces four tasks, namely Emotion Change Detection (ECD), Emotion State Identification (ESI), Emotion Transition Reasoning (ETR), and Next Emotion Prediction (NEP), forming a progressive evaluation framework from coarse-grained detection to deeper reasoning and prediction. We conduct a comprehensive evaluation of 18 state-of-the-art MLLMs on EmoTrans and obtain two main findings. First, although current MLLMs show relatively stronger performance on coarse-grained emotion change detection, they still struggle with fine-grained emotion dynamics modeling. Second, socially complex settings, especially multi-person scenarios, remain substantially challenging, while reasoning-oriented variants do not consistently yield clear improvements. To facilitate future research, we publicly release the benchmark, evaluation protocol, and code at https://github.com/Emo-gml/EmoTrans.

He Hu, Tengjin Weng, Zebang Cheng +5

Shenzhen University Shenzhen, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen, China · Queen Mary University of London +3

Multimodal Large Language ModelsMultimodal Model EvaluationAffective ComputingTemporal Video UnderstandingMultimodal Understanding
AskPDF
Apr 24, 2026

All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams

Disciplines such as business process management and process mining aid organizations by discovering insights about processes on the basis of recorded event data. However, an obstacle to process analysis is data multi-modality: for instance, data in video form are not directly interpretable as events. Existing approaches rely on a dictionary of activity label as input, cannot provide frame-by-frame labeling explanations, or rely on superseded computer vision techniques. In this work, we present SnapLog, an approach to extract event data from videos by converting frames to feature vectors using image embeddings and performing temporal segmentation through frame-wise similarity matrices. A generalized few-shot classification is then used to assign labels to the video segments, yielding labeled, timestamped sub-sequences of frames that are interpretable as events. Conventional process mining techniques can be used to analyze the resulting data. We show that our approach produces logs that accurately reflect the process in the videos.

Marco Pegoraro, Jonas Seng, Dustin Heller +2

Chair of Process and Data Science, RWTH Aachen University, Ahornstr. 55, 52074 Aachen, Germany · Artificial Intelligence & Machine Learning Lab, Technical University of Darmstadt, Hochschulstr. 1, 64289 Darmstadt, Germany

Process MiningTemporal Video Understanding
AskPDF
Apr 23, 2026

Seeing Fast and Slow: Learning the Flow of Time in Videos

How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern computer vision research, little attention has been paid to perceiving and controlling the passage of time. In this paper, we study time as a learnable visual concept and develop models for reasoning about and manipulating the flow of time in videos. We first exploit the multimodal cues and temporal structure naturally present in videos to learn, in a self-supervised manner, to detect speed changes and estimate playback speed. We then show that these learned temporal reasoning models enable us to curate the largest slow-motion video dataset to date from noisy in-the-wild sources. Such slow-motion footage, typically filmed by high-speed cameras, contains substantially richer temporal detail than standard videos. Using this data, we further develop models capable of temporal control, including speed-conditioned video generation, which produces motion at specified playback speed, and temporal super-resolution, which tranforms low-FPS, blurry videos into high-FPS sequences with fine-grained temporal details. Our findings highlight time as a manipulable, perceptual dimension in video learning, opening doors to temporally controllable video generation, temporal forensics detection, and potentially richer world-models that understand how events unfold over time.

Yen-Siang Wu, Rundong Luo, Jingsen Zhu +6

Cornell University · University of Washington · National Taiwan University

Controllable Video GenerationTemporal Video Understanding
AskPDF
Apr 23, 2026

Divide-then-Diagnose: Weaving Clinician-Inspired Contexts for Ultra-Long Capsule Endoscopy Videos

Capsule endoscopy (CE) enables non-invasive gastrointestinal screening, but current CE research remains largely limited to frame-level classification and detection, leaving video-level analysis underexplored. To bridge this gap, we introduce and formally define a new task, diagnosis-driven CE video summarization, which requires extracting key evidence frames that covers clinically meaningful findings and making accurate diagnoses from those evidence frames. This setting is challenging because diagnostically relevant events are extremely sparse and can be overwhelmed by tens of thousands of redundant normal frames, while individual observations are often ambiguous due to motion blur, debris, specular highlights, and rapid viewpoint changes. To facilitate research in this direction, we introduce VideoCAP, the first CE dataset with diagnosis-driven annotations derived from real clinical reports. VideoCAP comprises 240 full-length videos and provides realistic supervision for both key evidence frame extraction and diagnosis. To address this task, we further propose DiCE, a clinician-inspired framework that mirrors the standard CE reading workflow. DiCE first performs efficient candidate screening over the raw video, then uses a Context Weaver to organize candidates into coherent diagnostic contexts that preserve distinct lesion events, and an Evidence Converger to aggregate multi-frame evidence within each context into robust clip-level judgments. Experiments show that DiCE consistently outperforms state-of-the-art methods, producing concise and clinically reliable diagnostic summaries. These results highlight diagnosis-driven contextual reasoning as a promising paradigm for ultra-long CE video summarization.

Bowen Liu, Li Yang, Shanshan Song +6

1The Hong Kong University of Science and Technology · 2Renji Hospital, Shanghai Jiao Tong University School of Medicine

EndoscopyMedical ImagingMedical DiagnosisTemporal Video Understanding
AskPDF
Apr 23, 2026

HiCrew: Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration

Long-form video understanding remains fundamentally challenged by pervasive spatiotemporal redundancy and intricate narrative dependencies that span extended temporal horizons. While recent structured representations compress visual information effectively, they frequently sacrifice temporal coherence, which is critical for causal reasoning. Meanwhile, existing multi-agent frameworks operate through rigid, pre-defined workflows that fail to adapt their reasoning strategies to question-specific demands. In this paper, we introduce HiCrew, a hierarchical multi-agent framework that addresses these limitations through three core contributions. First, we propose a Hybrid Tree structure that leverages shot boundary detection to preserve temporal topology while performing relevance-guided hierarchical clustering within semantically coherent segments. Second, we develop a Question-Aware Captioning mechanism that synthesizes intent-driven visual prompts to generate precision-oriented semantic descriptions. Third, we integrate a Planning Layer that dynamically orchestrates agent collaboration by adaptively selecting roles and execution paths based on question complexity. Extensive experiments on EgoSchema and NExT-QA validate the effectiveness of our approach, demonstrating strong performance across diverse question types with particularly pronounced gains in temporal and causal reasoning tasks that benefit from our hierarchical structure-preserving design.

Yuehan Zhu, Jingqi Zhao, Jiawen Zhao +2

School of Artificial Intelligence, Sun Yat-sen University, China

Multi-Agent CollaborationMultimodal QALong-Video UnderstandingMulti-Agent ReasoningTemporal Video Understanding
AskPDF
Apr 22, 2026

Exploring High-Order Self-Similarity for Video Understanding

Space-time self-similarity (STSS), which captures visual correspondences across frames, provides an effective way to represent temporal dynamics for video understanding. In this work, we explore higher-order STSS and demonstrate how STSSs at different orders reveal distinct aspects of these dynamics. We then introduce the Multi-Order Self-Similarity (MOSS) module, a lightweight neural module designed to learn and integrate multi-order STSS features. It can be applied to diverse video tasks to enhance motion modeling capabilities while consuming only marginal computational cost and memory usage. Extensive experiments on video action recognition, motion-centric video VQA, and real-world robotic tasks consistently demonstrate substantial improvements, validating the broad applicability of MOSS as a general temporal modeling module. The source code and checkpoints will be publicly available.

Manjin Kim, Heeseung Kwon, Karteek Alahari +1

POSTECH · RLWRLD Inc. · INRIA Grenoble Rhône-Alpes

Spatiotemporal ReasoningVideo Action RecognitionTemporal Video Understanding
AskPDF
Apr 22, 2026

Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction

Micro-video popularity prediction (MVPP) aims to forecast the future popularity of videos on online media, which is essential for applications such as content recommendation and traffic allocation. In real-world scenarios, it is critical for MVPP approaches to understand both the temporal dynamics of a given video (temporal) and its historical relevance to other videos (spatial). However, existing approaches sufer from limitations in both dimensions: temporally, they rely on sparse short-range sampling that restricts content perception; spatially, they depend on flat retrieval memory with limited capacity and low efficiency, hindering scalable knowledge utilization. To overcome these limitations, we propose a unified framework that achieves joint spatio-temporal enlargement, enabling precise perception of extremely long video sequences while supporting a scalable memory bank that can infinitely expand to incorporate all relevant historical videos. Technically, we employ a Temporal Enlargement driven by a frame scoring module that extracts highlight cues from video frames through two complementary pathways: sparse sampling and dense perception. Their outputs are adaptively fused to enable robust long-sequence content understanding. For Spatial Enlargement, we construct a Topology-Aware Memory Bank that hierarchically clusters historically relevant content based on topological relationships. Instead of directly expanding memory capacity, we update the encoder features of the corresponding clusters when incorporating new videos, enabling unbounded historical association without unbounded storage growth. Extensive experiments on three widely used MVPP benchmarks demonstrate that our method consistently outperforms 11 strong baselines across mainstream metrics, achieving robust improvements in both prediction accuracy and ranking consistency.

Dali Wang, Yunyao Zhang, Junqing Yu +3

Huazhong University of Science and Technology Wuhan, China · La Trobe University Melbourne, Australia · Beijing Institute of Computer Technology and Applications Beijing, China

Social Media AnalysisMemory-Augmented Neural NetworksTemporal Video Understanding
AskPDF
Apr 20, 2026

EAST: Early Action Prediction Sampling Strategy with Token Masking

Early action prediction seeks to anticipate an action before it fully unfolds, but limited visual evidence makes this task especially challenging. We introduce EAST, a simple and efficient framework that enables a model to reason about incomplete observations. In our empirical study, we identify key components when training early action prediction models. Our key contribution is a randomized training strategy that samples a time step separating observed and unobserved video frames, enabling a single model to generalize seamlessly across all test-time observation ratios. We further show that joint learning on both observed and future (oracle) representations significantly boosts performance, even allowing an encoder-only model to excel. To improve scalability, we propose a token masking procedure that cuts memory usage in half and accelerates training by 2x with negligible accuracy loss. Combined with a forecasting decoder, EAST sets a new state of the art on NTU60, SSv2, and UCF101, surpassing previous best work by 10.1, 7.7, and 3.9 percentage points, respectively.

Iva Sović, Ivan Martinović, Marin Oršić

Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia

Video Action RecognitionTemporal Video Understanding
AskPDF