{"total":84,"rows":[{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131,"area":null},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107,"area":null},{"id":"2105.11107","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2312.00589","title":"Merlin:Empowering Multimodal LLMs with Foresight Minds","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2401.01505","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","created":"2024-01-03","cited_by_count":41,"area":null},{"id":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","cited_by_count":40,"area":null},{"id":"2512.10863","title":"MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence","created":"2025-12-11","cited_by_count":38,"area":null},{"id":"2404.05029","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","created":"2024-04-07","cited_by_count":31,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2210.12686","title":"Holistic Interaction Transformer Network for Action Detection","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2405.06887","title":"FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment","created":"2024-05-11","cited_by_count":25,"area":null},{"id":"2410.08474","title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","created":"2024-10-11","cited_by_count":24,"area":"mllm"},{"id":"2303.15879","title":"STMixer: A One-Stage Sparse Action Detector","created":"2023-03-28","cited_by_count":22,"area":null},{"id":"2304.08451","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","created":"2023-04-17","cited_by_count":20,"area":null},{"id":"2304.12160","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","created":"2023-04-24","cited_by_count":20,"area":null},{"id":"2306.02585","title":"MotionTrack: Learning Motion Predictor for Multiple Object Tracking","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2310.13347","title":"NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding","created":"2023-10-20","cited_by_count":20,"area":null},{"id":"2404.00653","title":"Dual DETRs for Multi-Label Temporal Action Detection","created":"2024-03-31","cited_by_count":20,"area":null},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17,"area":null},{"id":"2303.16268","title":"TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2306.04948","title":"ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis","created":"2023-06-08","cited_by_count":15,"area":null},{"id":"2404.04565","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","created":"2024-04-06","cited_by_count":15,"area":null},{"id":"2209.02250","title":"Spatio-Temporal Action Detection Under Large Motion","created":"2022-09-06","cited_by_count":14,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2503.07860","title":"Video Action Differencing","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2203.03806","title":"Panoramic Human Activity Recognition","created":"2022-03-08","cited_by_count":13,"area":null},{"id":"2205.13313","title":"Cross-Architecture Self-supervised Video Representation Learning","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2406.12252","title":"Language and Multimodal Models in Sports: A Survey of Datasets and Applications","created":"2024-06-18","cited_by_count":10,"area":null},{"id":"2512.11016","title":"SoccerMaster: A Vision Foundation Model for Soccer Understanding","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2411.10922","title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2309.12067","title":"Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives","created":"2023-09-21","cited_by_count":7,"area":null},{"id":"2206.03064","title":"A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action Detector","created":"2022-06-07","cited_by_count":6,"area":null},{"id":"2406.14877","title":"Sports Intelligence: Assessing the Sports Understanding Capabilities of Language Models through Question Answering from Text to Video","created":"2024-06-21","cited_by_count":6,"area":null},{"id":"2502.15462","title":"Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networks","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2507.22061","title":"MOVE: Motion-Guided Few-Shot Video Object Segmentation","created":"2025-07-29","cited_by_count":6,"area":null},{"id":"2308.01618","title":"A Survey on Deep Learning-based Spatio-temporal Action Detection","created":"2023-08-03","cited_by_count":5,"area":null},{"id":"2505.09455","title":"Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos","created":"2025-05-14","cited_by_count":5,"area":null},{"id":"2511.16183","title":"FOOTPASS: A Multi-Modal Multi-Agent Tactical Context Dataset for Play-by-Play Action Spotting in Soccer Broadcast Videos","created":"2025-11-20","cited_by_count":5,"area":null},{"id":"2606.02522","title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","created":"2026-06-01","cited_by_count":5,"area":"mllm"},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2503.06522","title":"SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2510.11204","title":"Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2303.16053","title":"Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2303.16118","title":"CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2307.02730","title":"Fine-grained Action Analysis: A Multi-modality and Multi-task Dataset of Figure Skating","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2605.10543","title":"TIE: Time Interval Encoding for Video Generation over Events","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2209.15439","title":"Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection","created":"2022-09-28","cited_by_count":2,"area":null},{"id":"2310.17493","title":"A Hybrid Graph Network for Complex Activity Detection in Video","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2409.00926","title":"Towards Student Actions in Classroom Scenes: New Dataset and Baseline","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2204.02688","title":"MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization","created":"2022-04-06","cited_by_count":1,"area":null},{"id":"2204.10160","title":"A Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions","created":"2022-04-21","cited_by_count":1,"area":null},{"id":"2305.15692","title":"Deep Neural Networks in Video Human Action Recognition: A Review","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2309.11445","title":"SkeleTR: Towrads Skeleton-based Action Recognition in the Wild","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2309.13962","title":"Egocentric RGB+Depth Action Recognition in Industry-Like Settings","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2411.01683","title":"ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving","created":"2024-11-03","cited_by_count":1,"area":null},{"id":"2504.08175","title":"Multi-person Physics-based Pose Estimation for Combat Sports","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2509.21783","title":"Prompt-guided Disentangled Representation for Action Recognition","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2608.23435","title":"Towards Comprehensive Basketball Understanding","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2307.13541","title":"Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2310.16267","title":"Student Classroom Behavior Detection based on Spatio-Temporal Network and Multi-Model Fusion","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2404.09842","title":"STMixer: A One-Stage Sparse Action Detector","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2502.09967","title":"VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2503.08933","title":"PromptGAR: Flexible Promptive Group Activity Recognition","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2504.03096","title":"Scaling Open-Vocabulary Action Detection","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2507.10969","title":"Women Sport Actions Dataset for Visual Classification Using Small Scale Training Data","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2508.01802","title":"SoccerTrack v2: A Full-Pitch Panoramic Video Dataset for Game State Reconstruction and Ball Action Spotting","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2509.20715","title":"Beyond the Individual: Introducing Group Intention Forecasting with SHOT Dataset","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2605.02834","title":"VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.23118","title":"LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.29230","title":"Again-Pose: Anchor-Guided Adaptive Inter-Frame Motion Cues Propagating for High-quality Human Pose Reconstruction","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.02269","title":"AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"id":"2607.04684","title":"TubeLite: Lightweight Multi-Actor Spatio-Temporal Action Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.21267","title":"BasketEvent: Understanding Who Did What and When in Basketball Videos","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.26097","title":"Knowledge-guided Disentanglement with Atomic Actions for Action Recognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.28049","title":"Prompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings","created":"2026-09-23","cited_by_count":0,"area":"wm"},{"id":"2609.34547","title":"ActionLens: Diagnosing Spatial-Temporal Binding Failures in Vision-Language Models","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2610.16383","title":"Throwing4: Phase-Aware Pose Modeling for Throw-Distance Prediction in Elite Athletics","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18829","title":"OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}