Temporal Video Understanding

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
View on map

Latest papers 220

All topics
CardsList

  1. T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video

    Jul 23, 2026Linlin Wang, Xue Yang, Zhihuang Zhou +3Video UnderstandingScene Graph Generation

    School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China · School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China

  2. ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?

    Jul 23, 2026Han Li, Si Liu, Zehao Huang +6VLM EvaluationSpatial Reasoning Benchmarks

    School of Artificial Intelligence, Beihang University, Beijing 100191, China · Zhongguancun Academy, Beijing 100094, China · School of Engineering, Westlake University, Hangzhou 310030, China

  3. PercepCap: Video Captioner with Structured Spatio-Temporal Perception

    Jul 22, 2026Yifan Xu, Zihao Wang, Zhixiao Wang +6Video CaptioningTemporal Video Understanding

    State Key Laboratory for Novel Software Technology, Nanjing Univerisity · Kling Team, Kuaishou Technology · Shanghai AI Laboratory

  4. ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning

    Jul 21, 2026Santiram Tiwari, Nishant Sinha, Kunal KislayMemory-Augmented VLMsKV Caching

    KGraph AI Solutions Pvt. Ltd., Bangalore, India – 560016

  5. HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization

    Jul 20, 2026Rui Chu, Yingjie LaoVideo SummarizationMultimodal Large Language Models

    Tufts University, Medford, MA, USA

  6. Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection

    Jul 20, 2026Amir Hosein Fadaei, Mahyar Maleki, Mohammad-Reza A. DehaqaniTransformerEfficient ViTs

    University of Tehran, Faculty of Electrical and Computer Engineering, North Kargar st., Tehran, 1439957131, Tehran, Iran

  7. HTT-Net: Hierarchical Text-guided Transition Modeling for Surgical Video Phase Recognition

    Jul 18, 2026Kunjie Deng, Jinghui Zhang, Weidong Chen +4Surgical Video UnderstandingTemporal Video Understanding

  8. Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding

    Jul 17, 2026Wei Feng, Xin Wang, Yu-Wei Zhan +2Temporal Video GroundingVideo-Language Models

    Department of Computer Science and Technology, Tsinghua University · Beijing National Research Center for Information Science and Technology, Tsinghua University

  9. VideoSEMA: a scalable and efficient Mamba-like attention for video understanding

    Jul 16, 2026Nhat Thanh Tran, Fanghui Xue andShuai Zhang, Jiancheng Lyu +3Efficient ViTsEfficient Attention

    Department of Mathematics University of California, Irvine Irvine, USA · Qualcomm AI Research San Diego, USA

  10. Towards Spatial Supersensing in the Wild

    Jul 15, 2026Tianjun Gu, Tianyu Xin, Kuan Zhang +12Long-Video UnderstandingWorld Model Evaluation

    Tsinghua University · NVIDIA · Stanford University

  11. GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning

    Jul 15, 2026Kaicong Huang, Weiheng Oh, Ruimin KeZero-Shot LearningVision-Language Grounding

    Rensselaer Polytechnic Institute Troy, NY, USA

  12. Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks

    Jul 14, 2026Jae Joong LeeVLM EvaluationVideo-Language Model Evaluation

    Department of Computer Science Purdue University West Lafayette, Indiana, USA

  13. Gaussian Mixture Modeling for Event-Aware Visual Allocation in Long Video Understanding

    Jul 14, 2026Yifan Lu, Ziqi Zhang, Chunfeng Yuan +3Large Vision-Language ModelsVideo Frame Selection

    Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information, CASIA · State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA · School of Artificial Intelligence, University of Chinese Academy of Sciences +2

  14. What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation

    Jul 14, 2026Farrukh RahmanVLM EvaluationTemporal Reasoning

    Microsoft · Georgia Institute of Technology

  15. Do Video-LLMs Actually Watch? Diagnosing Character-Tracking Failures in Long-Form Video

    Jul 13, 2026Mohammad Al-Ratrout, Shayla Sharmin, Aditya Raikwar +1Visual Object TrackingVideo-Language Model Evaluation

  16. Anomalous Frame Detection Using VLM-Based Description Comparison for Extracting Expert-Specific Actions and Contextual Decision-Making Scenes with Intra-Video Self-Similarity

    Jul 12, 2026Ryo Sakai, Kaname YokoyamaVideo Anomaly DetectionTemporal Video Understanding

    Robotics Research Department, Research and Development Group, Hitachi, Ltd., Ibaraki, Japan

  17. GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language Models

    Jul 10, 2026Guohuan Xie, Mengqi Lei, Chuan Shi +3Efficient VLM InferenceVideo-Language Models

    BNRist, THUIBCS, BLBCI, School of Software, Tsinghua University · Yangtze Delta Region Institute, Tsinghua University · Beijing University of Posts and Telecommunications, Beijing, China

  18. AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding

    Jul 9, 2026Siddharth Damodharan, Radhika Gupta, Ali Alshami +2VLM EvaluationAutonomous Driving Benchmarks

    University of Colorado Colorado Springs · University of Michigan · University of Notre Dame

  19. Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

    Jul 6, 2026Chang Nie, Jiaju Wei, Junlan Feng +2Multimodal AgentsMemory-Augmented Agents

    Nanjing University

  20. TubeLite: Lightweight Multi-Actor Spatio-Temporal Action Detection

    Jul 6, 2026Ali Soltaninezhad, Melissa Cote, Alejandro Rico Espinosa +2Temporal Action DetectionTemporal Video Understanding

    Electrical and Computer Engineering, University of Victoria, Victoria, BC, Canada

  21. Event Detection in Videos: A Framework for the Development of New Methods

    Jul 5, 2026Anastasia Zakharova, Thierry Bouwmans, Anthony Cioppa +13Video SurveillanceTemporal Video Understanding

    MIA lab of the La Rochelle University, France · Montefiore Institute of the University of Liège, Belgium · DIEM Department of the University of Salerno, Italy +5

  22. DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics

    Jul 5, 2026Silin Gao, Hao Zhao, Zeming Chen +8Video World ModelsTemporal Video Understanding

  23. A Multi-Task Deep Learning Framework for Real-Time Intelligent Video Surveillance with Temporal Event Validation

    Jul 3, 2026Estera Dumitru, Stelian SpînuVideo Action RecognitionObject Detection

    Faculty of Information Systems and Cyber Security Military Technical Academy “Ferdinand I” Bucharest, Romania

  24. Rank-Then-Act: Reward-Free Control from Frame-Order Progress

    Jul 2, 2026Yuriy Maksyuta, George Bredis, Ruslan Rakhimov +1RL ControlReward Modeling

    T-Tech

  25. MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding

    Jul 2, 2026Yuan Wang, Shujian Gao, Songtao Jiang +2Video UnderstandingStreaming Video Understanding

    College of Computer Science and Technology, Zhejiang University, Zhejiang, China · Insititute of Trustworthy Embodied AI, Fudan University, Shanghai, China · Department of Electrical and Computer Engineering, Carnegie Mellon University, Pennsylvania, USA

  26. Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning

    Jul 2, 2026Chen Zhao, Jiajun Ma, Qilong Huang +6Audio-Visual UnderstandingVideo Captioning

    Meituan, China · Nanjing University, State Key Laboratory for Novel Software Technology, China

  27. OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization

    Jul 1, 2026Sakib Reza, Gauri Jagatap, Mohsen Moghaddam +2Knowledge DistillationTemporal Video Understanding

    Northeastern University, Boston, MA 02115, USA · Georgia Institute of Technology, Atlanta, GA 30332, USA · Dolby Laboratories +1

  28. No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs

    Jun 30, 2026Haojian Huang, Harold Haodong Chen, Meng Luo +6VLM EvaluationMultimodal Hallucination

    The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Knowin AI, China · National University of Singapore, Singapore +4

  29. Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors

    Jun 30, 2026Karam Tomotaki-Dawoud, Anna Hilsmann, Peter Eisert +1Video Object DetectionReal-Time Object Detection

    Fraunhofer HHI, Berlin, Germany

  30. Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition

    Jun 30, 2026Xiaochuan Guo, Jihao Gu, Haixu Liu +6Few-Shot LearningMultimodal Emotion Recognition

    Hefei University of Technology, China · University College London, United Kingdom · The University of Sydney, Australia +5