{"total":150,"rows":[{"id":"2307.15700","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","created":"2023-07-28","cited_by_count":88,"area":null},{"id":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80,"area":null},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57,"area":null},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2104.09333","title":"Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting","created":"2021-04-19","cited_by_count":43,"area":null},{"id":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"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":"2304.04617","title":"VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views","created":"2023-04-10","cited_by_count":38,"area":null},{"id":"2208.08190","title":"DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations","created":"2022-08-17","cited_by_count":37,"area":null},{"id":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37,"area":null},{"id":"2109.02613","title":"Class Semantics-based Attention for Action Detection","created":"2021-09-06","cited_by_count":36,"area":null},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32,"area":null},{"id":"2104.06779","title":"Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts","created":"2021-04-14","cited_by_count":30,"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":"2210.02365","title":"SoccerNet 2022 Challenges Results","created":"2022-10-05","cited_by_count":28,"area":null},{"id":"2106.14447","title":"Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection","created":"2021-06-28","cited_by_count":27,"area":null},{"id":"2205.10450","title":"Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors","created":"2022-05-20","cited_by_count":27,"area":null},{"id":"2503.13956","title":"Improving LLM Video Understanding with 16 Frames Per Second","created":"2025-03-18","cited_by_count":26,"area":"mllm"},{"id":"2204.06859","title":"Semi-Supervised Training to Improve Player and Ball Detection in Soccer","created":"2022-04-14","cited_by_count":25,"area":null},{"id":"2511.05299","title":"LiveStar: Live Streaming Assistant for Real-World Online Video Understanding","created":"2025-11-07","cited_by_count":25,"area":null},{"id":"2404.06332","title":"X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model","created":"2024-04-07","cited_by_count":22,"area":"mllm"},{"id":"2203.02281","title":"A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions","created":"2022-03-03","cited_by_count":21,"area":null},{"id":"2404.05392","title":"T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos","created":"2024-04-08","cited_by_count":21,"area":null},{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21,"area":null},{"id":"2309.06006","title":"SoccerNet 2023 Challenges Results","created":"2023-09-12","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":"2102.07624","title":"RMS-Net: Regression and Masking for Soccer Event Spotting","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2505.03735","title":"Multi-Agent System for Comprehensive Soccer Understanding","created":"2025-05-06","cited_by_count":18,"area":"agents"},{"id":"2104.10068","title":"Contrastive Learning for Sports Video: Unsupervised Player Classification","created":"2021-04-15","cited_by_count":17,"area":null},{"id":"2309.01270","title":"COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers","created":"2023-09-03","cited_by_count":17,"area":"distill"},{"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":"2405.12070","title":"AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements","created":"2024-05-20","cited_by_count":15,"area":null},{"id":"2111.11535","title":"Ice hockey player identification via transformers and weakly supervised learning","created":"2021-11-22","cited_by_count":14,"area":null},{"id":"2206.07846","title":"Action Spotting using Dense Detection Anchors Revisited: Submission to the SoccerNet Challenge 2022","created":"2022-06-15","cited_by_count":14,"area":null},{"id":"2304.04220","title":"Towards Active Learning for Action Spotting in Association Football Videos","created":"2023-04-09","cited_by_count":14,"area":null},{"id":"2404.09807","title":"A Universal Protocol to Benchmark Camera Calibration for Sports","created":"2024-04-15","cited_by_count":14,"area":null},{"id":"2501.02771","title":"WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation","created":"2025-01-06","cited_by_count":14,"area":null},{"id":"2504.17365","title":"TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation","created":"2025-04-24","cited_by_count":13,"area":"mllm"},{"id":"2405.07354","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","created":"2024-05-12","cited_by_count":12,"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":"2404.01051","title":"Action Detection via an Image Diffusion Process","created":"2024-04-01","cited_by_count":11,"area":null},{"id":"2202.00804","title":"Automatic event detection in football using tracking data","created":"2022-02-01","cited_by_count":10,"area":null},{"id":"2204.02674","title":"Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2211.12334","title":"A Graph-Based Method for Soccer Action Spotting Using Unsupervised Player Classification","created":"2022-11-22","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":"2205.05487","title":"Scene Consistency Representation Learning for Video Scene Segmentation","created":"2022-05-11","cited_by_count":9,"area":null},{"id":"2504.12021","title":"Action Anticipation from SoccerNet Football Video Broadcasts","created":"2025-04-16","cited_by_count":9,"area":null},{"id":"2404.09951","title":"Unifying Global and Local Scene Entities Modelling for Precise Action Spotting","created":"2024-04-15","cited_by_count":8,"area":null},{"id":"2407.12483","title":"Towards AI-Powered Video Assistant Referee System (VARS) for Association Football","created":"2024-07-17","cited_by_count":8,"area":null},{"id":"2409.10587","title":"SoccerNet 2024 Challenges Results","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2505.16630","title":"SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding","created":"2025-05-22","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":"2402.09650","title":"Foul prediction with estimated poses from soccer broadcast video","created":"2024-02-15","cited_by_count":7,"area":null},{"id":"2408.16638","title":"3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach","created":"2024-08-29","cited_by_count":7,"area":null},{"id":"2410.01304","title":"Deep learning for action spotting in association football videos","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2502.02785","title":"OpenSTARLab: Open Approach for Spatio-Temporal Agent Data Analysis in Soccer","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2505.13860","title":"Domain Adaptation of VLM for Soccer Video Understanding","created":"2025-05-20","cited_by_count":7,"area":"mllm"},{"id":"2105.10563","title":"Puck localization and multi-task event recognition in broadcast hockey videos","created":"2021-05-21","cited_by_count":6,"area":null},{"id":"2503.00147","title":"Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance","created":"2025-02-28","cited_by_count":6,"area":null},{"id":"2504.19514","title":"FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2412.01721","title":"BroadTrack: Broadcast Camera Tracking for Soccer","created":"2024-12-02","cited_by_count":5,"area":null},{"id":"2412.21205","title":"Action-Agnostic Point-Level Supervision for Temporal Action Detection","created":"2024-12-30","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":"2108.11149","title":"A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games","created":"2021-08-25","cited_by_count":4,"area":null},{"id":"2504.10106","title":"SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene Understanding","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2508.19182","title":"SoccerNet 2025 Challenges Results","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2312.15236","title":"Classifying Soccer Ball-on-Goal Position Through Kicker Shooting Action","created":"2023-12-23","cited_by_count":3,"area":null},{"id":"2406.12081","title":"Deep HM-SORT: Enhancing Multi-Object Tracking in Sports with Deep Features, Harmonic Mean, and Expansion IOU","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2501.16100","title":"Automated Detection of Sport Highlights from Audio and Video Sources","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2505.03991","title":"Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challenges","created":"2025-05-06","cited_by_count":3,"area":null},{"id":"2506.17294","title":"From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentary","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2507.17844","title":"SV3.3B: A Sports Video Understanding Model for Action Recognition","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2509.01439","title":"SoccerHigh: A Benchmark Dataset for Automatic Soccer Video Summarization","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2510.19150","title":"X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2601.23232","title":"ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2604.11786","title":"GenTac: Generative Modeling and Forecasting of Soccer Tactics","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2105.09880","title":"DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera","created":"2021-05-20","cited_by_count":2,"area":null},{"id":"2106.00359","title":"Learning Football Body-Orientation as a Matter of Classification","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2111.00629","title":"Distantly Supervised Semantic Text Detection and Recognition for Broadcast Sports Videos Understanding","created":"2021-10-31","cited_by_count":2,"area":null},{"id":"2407.01265","title":"OSL-ActionSpotting: A Unified Library for Action Spotting in Sports Videos","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2501.09281","title":"SoccerSynth-Detection: A Synthetic Dataset for Soccer Player Detection","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2504.12045","title":"pix2pockets: Shot Suggestions in 8-Ball Pool from a Single Image in the Wild","created":"2025-04-16","cited_by_count":2,"area":"deeprl"},{"id":"2506.03335","title":"SportMamba: Adaptive Non-Linear Multi-Object Tracking with State Space Models for Team Sports","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2510.06973","title":"Addressing the ID-Matching Challenge in Long Video Captioning","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2511.12606","title":"Pixels or Positions? Benchmarking Modalities in Group Activity Recognition","created":"2025-11-16","cited_by_count":2,"area":null},{"id":"2512.10918","title":"CompanionCast: Toward Social Collaboration with Multi-Agent Systems in Shared Experiences","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2603.09896","title":"Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2604.12343","title":"Detecting Precise Hand Touch Moments in Egocentric Video","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2606.17798","title":"LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams","created":"2026-06-16","cited_by_count":2,"area":"inference"},{"id":"2111.08954","title":"Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers","created":"2021-11-17","cited_by_count":1,"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":"2205.00694","title":"A Multi-stage deep architecture for summary generation of soccer videos","created":"2022-05-02","cited_by_count":1,"area":null},{"id":"2310.11700","title":"Runner re-identification from single-view running video in the open-world setting","created":"2023-10-18","cited_by_count":1,"area":null},{"id":"2310.13585","title":"POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2407.02370","title":"Investigating Event-Based Cameras for Video Frame Interpolation in Sports","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2507.07381","title":"Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2511.09448","title":"MCAD: Multimodal Context-Aware Audio Description Generation For Soccer","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2601.08557","title":"VideoHEDGE: Entropy-Based Hallucination Detection for Video-VLMs via Semantic Clustering and Spatiotemporal Perturbations","created":"2026-01-13","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}