Temporal Action Localization

Ask about this topic

Overview

Temporal action localization identifies which actions occur in a long video and when each begins and ends, supporting tasks such as video search, sports analysis, and surgical monitoring. Methods use temporal CNNs, transformers, or state-space models to predict action segments, while language-guided grounding and proposal reranking connect video intervals to text queries. Because precise frame-level labels are costly, work also explores weak, point-level, unsupervised, and zero-shot learning, alongside online localization for streaming video. Benchmarks such as THUMOS14 and ActivityNet evaluate detection with mean average precision at different temporal IoU thresholds; a central challenge is balancing accurate boundaries and generalization to new actions against limited supervision and computational cost.

Latest papers

CardsList

32 papers5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

  1. Learning High-Quality Pseudo-Labels for Point-Supervised Temporal Action Localization

    Oct 26, 2026Zhenying FangTemporal Action LocalizationTemporal Video Understanding

    Independent Researcher

  2. P2P-Former: Bridging the Supervision Gap Between Point and Proposal in Temporal Action Localization

    Oct 25, 2026Yunchuan Ma, Laiyun Qing, Sai Xu +2Temporal Action LocalizationTemporal Video Understanding

    University of Chinese Academy of Sciences, Beijing,100190, China

  3. DeformStruct: Deformable Structure Modeling for Point-Supervised Temporal Action Localization

    Oct 23, 2026Mengnan Liu, Sanping Zhou, Kun Xia +3Temporal Action LocalizationTemporal Video Understanding

    State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China · School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China · School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, China +2

  4. CoDy: Codec Dynamics as Complementary Priors for Unsupervised Temporal Action Localization

    Oct 14, 2026Tianyu Yan, Qingyi Yang, Qin Yang +5Temporal Action LocalizationVideo Understanding

    School of Computer Science and Technology, Huazhong University of Science and Technology · Huawei Technologies Ltd

  5. FPV-CRASH: A Dataset for Offline Crash Moment Localization in Drone First-Person-View Videos

    Oct 14, 2026Jifan Zhang, Tingyu Wang, Qian Liu +1Temporal Action LocalizationAerial Robotics

    School of Communication Engineering, Hangzhou Dianzi University, China. · School of Computer Science, Faculty of Science, University of Auckland, Auckland, New Zealand. · Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau, China.

  6. HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding

    Oct 14, 2026Rui Chen, Xingyu Chen, Pengxin Xu +2Temporal Action DetectionTemporal Video Understanding

    Peking University · Zhongguancun Academy · Harbin Institute of Technology, Shenzhen +1

  7. Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding

    Sep 21, 2026Yu-Ho Chang, Chi-Hsi Kung, Yi-Hsuan Tsai +1Autonomous Driving PerceptionVideo Action Recognition

    National Yang Ming Chiao Tung University · Atmanity Inc.

  8. PSEE: Progressive Sensor Event Expansion for Point-Supervised Temporal Action Localization

    Sep 18, 2026Jiaxi Yin, Ge Wang, Han Ding +1Temporal Action LocalizationHuman Activity Recognition

    Xi’an Jiaotong University, Xi’an, China

  9. OphBiWSSD: Scaling Temporal Action Localization in Ophthalmic Surgeries with Bidirectional Weight-tied State Space Duality

    Sep 11, 2026Yang Liu, Qionghong Ma, Joongwon Chae +10Surgical Video UnderstandingTemporal Action Detection

    Institute of Biopharmaceutics and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China · Department of Ophthalmology, The Fifth Affiliated Hospital of Wenzhou Medical University, Wenzhou Medical University, Lishui 323000, China · School of Optometry, The Hong Kong Polytechnic University +4

  10. Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining

    Aug 26, 2026Koshiro Nagano, Fumiaki Sato, Ryo Hachiuma +2Temporal Action LocalizationZero-Shot Learning

    Konica Minolta, Inc. · Keio University · CyberAgent +1

  11. PL-NBA: A Possession-level Universal Basketball Video Dataset Supporting Multiple Visual Understanding Tasks

    Aug 20, 2026Yunhao Zhao, Haoying Sun, Jiarui Li +5Sports Video AnalysisVideo Action Recognition

    Beijing University of Technology Beijing, China · Nanjing University of Science and Technology Nanjing, China · Hong Kong Polytechnic University Hong Kong, China

  12. Your VLM Already Knows When: Training-Free Temporal Grounding by Asking Yes or No

    Aug 8, 2026Ji Huang, Barry Devereux, Hui WangTemporal Video GroundingTemporal Reasoning in Language Models

    Queen’s University Belfast

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

    Aug 3, 2026Cheng-Yao Hong, Ting-Wei Lin, Yun-Chung Lai +3Event-Based VisionVideo Action Recognition

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

  14. Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data

    Jul 10, 2026Valentin Gabeff, Baptiste Maquignaz, Jennifer Shan +5Vision-Language RetrievalWildlife Monitoring

    Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland · Max Planck Institute of Animal Behavior, Konstanz, Germany · University of Konstanz, Konstanz, Germany

  15. 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

  16. SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos

    Jun 30, 2026Björn Braun, Christian HolzEgocentric Video UnderstandingTemporal Action Detection

    Department of Computer Science, ETH Zürich, Switzerland

  17. ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization

    May 29, 2026Kanchan Keisham, Thenukan Pathmanathan, Thangarajah AkilanZero-Shot LearningHybrid CNN-Transformer Architectures

    Vellore Institute of Technology, India · Lakehead University, Canada

  18. Masked Diffusion Vision-Language Models for Temporal Action Localization

    May 28, 2026Fengshun Wang, Zhengbo Zhang, Zhigang TuTemporal Action DetectionTemporal Action Localization

    Wuhan University · Singapore University of Technology and Design

  19. EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026

    May 23, 2026Zhiheng Fu, Zixu Li, Zhiwei Chen +4Egocentric Video UnderstandingVideo Action Recognition

    1Shandong University · 2Harbin Institute of Technology (Shenzhen)

  20. Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization

    May 22, 2026Tianyu Wang, Junjie Wu, Jingquan Gao +1Sports Video AnalysisTemporal Action Detection

    School of Economics and Management, Beihang University, Beijing 100191, China · Key Laboratory of Data Intelligence and Management, Beihang University, Ministry of Industry and Information Technology, Beijing 100191, China

  21. Zero-Shot Temporal Action Localization Through Textual Guidance

    May 21, 2026Benedetta Liberatori, Alessandro Conti, Lorenzo Vaquero +3Zero-Shot LearningTemporal Action Detection

    University of Trento, Trento, Italy · Fondazione Bruno Kessler, Trento, Italy

  22. OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026

    May 20, 2026Yisen Feng, Leigang Qu, Haoyu Zhang +5Temporal Video GroundingMultimodal Reranking

    Harbin Institute of Technology (Shenzhen) · National University of Singapore · Pengcheng Laboratory +2

  23. LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation

    Apr 20, 2026Zepeng Sun, Naichuan Zheng, Hailun Xia +3Liquid Neural NetworksHuman Activity Recognition

  24. Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detection

    Apr 10, 2026Yicheng Qiu, Keiji YanaiTemporal Action DetectionTemporal Action Localization

    Department of Informatics The University of Electro-Communications Chofu, Tokyo, Japan

  25. GRAZE: Grounded Refinement and Motion-Aware Zero-Shot Event Localization

    Apr 1, 2026Syed Ahsan Masud Zaidi, Lior Shamir, William Hsu +2Sports Video AnalysisTemporal Action Localization

    Kansas State University, Manhattan, KS, USA · Albright College, Reading, PA, USA

  26. RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization

    Mar 25, 2026Ting Yu Tsai, An Yu, Lucy Lee +5Animal Behavior AnalysisTemporal Action Localization

    University at Albany, SUNY · University of Louisville · GE HealthCare

  27. A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors

    Mar 22, 2026Gia-Bao Doan, Nam-Khoa Huynh, Minh-Nhat-Huy Ho +3Driver MonitoringTemporal Video Understanding

    Department of Information Technology FPT University Ho Chi Minh City 700000, Vietnam · Faculty of Electronics Technology Industrial University of Ho Chi Minh City Ho Chi Minh City 700000, Vietnam · School of Computer Science and Engineering The Saigon International University Ho Chi Minh City 700000, Vietnam

  28. SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion

    Mar 13, 2026Xiang Li, Heqian Qiu, Lanxiao Wang +4Egocentric Video UnderstandingTemporal Action Localization

    University of Electronic Sience and Technology of China Chengdu, China

  29. AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting

    Feb 25, 2026Artur Xarles, Sergio Escalera, Thomas B. Moeslund +1Temporal Action LocalizationSports Video Analysis

    Universitat de Barcelona, Barcelona, Spain · Computer Vision Center, Cerdanyola del Vall`es, Spain · Aalborg University, Aalborg, Denmark

  30. Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization

    Feb 5, 2026Yunchuan Ma, Laiyun Qing, Guorong Li +3Weakly Supervised LearningTemporal Consistency

    University of Chinese Academy of Sciences, Beijing, 100190, China · Macquarie University