{"total":131,"rows":[{"id":"2302.08890","title":"Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks","created":"2023-02-17","cited_by_count":90,"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":"2211.14317","title":"Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space","created":"2022-11-24","cited_by_count":66,"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":"2310.10553","title":"TacticAI: an AI assistant for football tactics","created":"2023-10-16","cited_by_count":44,"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":"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":"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":"2404.11335","title":"SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap","created":"2024-04-17","cited_by_count":34,"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":"2303.14655","title":"GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation","created":"2023-03-26","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":"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":"2207.11709","title":"TVCalib: Camera Calibration for Sports Field Registration in Soccer","created":"2022-07-24","cited_by_count":22,"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":"2206.01899","title":"Evaluation of creating scoring opportunities for teammates in soccer via trajectory prediction","created":"2022-06-04","cited_by_count":20,"area":null},{"id":"2309.06006","title":"SoccerNet 2023 Challenges Results","created":"2023-09-12","cited_by_count":20,"area":null},{"id":"2505.03735","title":"Multi-Agent System for Comprehensive Soccer Understanding","created":"2025-05-06","cited_by_count":18,"area":"agents"},{"id":"2204.04049","title":"Efficient tracking of team sport players with few game-specific annotations","created":"2022-04-08","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":"2404.01891","title":"ASTRA: An Action Spotting TRAnsformer for Soccer Videos","created":"2024-04-02","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":"2405.12070","title":"AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements","created":"2024-05-20","cited_by_count":15,"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":"2404.08401","title":"PnLCalib: Sports Field Registration via Points and Lines Optimization","created":"2024-04-12","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":"2203.00307","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","created":"2022-03-01","cited_by_count":12,"area":null},{"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":"2202.00804","title":"Automatic event detection in football using tracking data","created":"2022-02-01","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":"2504.12021","title":"Action Anticipation from SoccerNet Football Video Broadcasts","created":"2025-04-16","cited_by_count":9,"area":null},{"id":"2603.12254","title":"Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing","created":"2026-03-12","cited_by_count":9,"area":"mllm"},{"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":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"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":"2407.12622","title":"Rethinking the Architecture Design for Efficient Generic Event Boundary Detection","created":"2024-07-17","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":"2412.17637","title":"SCBench: A Sports Commentary Benchmark for Video LLMs","created":"2024-12-23","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":"2504.08222","title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","created":"2025-04-11","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":"2603.19054","title":"Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2206.02373","title":"Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports","created":"2022-06-06","cited_by_count":6,"area":null},{"id":"2305.04247","title":"Estimation of control area in badminton doubles with pose information from top and back view drone videos","created":"2023-05-07","cited_by_count":6,"area":null},{"id":"2402.00163","title":"Improving Object Detection Quality in Football Through Super-Resolution Techniques","created":"2024-01-31","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":"2207.12730","title":"P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos","created":"2022-07-26","cited_by_count":5,"area":null},{"id":"2412.01721","title":"BroadTrack: Broadcast Camera Tracking for Soccer","created":"2024-12-02","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":"2202.05728","title":"Deep soccer captioning with transformer: dataset, semantics-related losses, and multi-level evaluation","created":"2022-02-11","cited_by_count":4,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2209.07795","title":"KaliCalib: A Framework for Basketball Court Registration","created":"2022-09-16","cited_by_count":3,"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":"2411.16804","title":"InTraGen: Trajectory-controlled Video Generation for Object Interactions","created":"2024-11-25","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":"2509.15602","title":"TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?","created":"2025-09-19","cited_by_count":3,"area":"mllm"},{"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":"2604.02020","title":"Are VLMs Lost Between Sky and Space? LinkS$^2$Bench for UAV-Satellite Dynamic Cross-View Spatial Intelligence","created":"2026-04-02","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":"2106.00359","title":"Learning Football Body-Orientation as a Matter of Classification","created":"2021-06-01","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":"2409.17580","title":"Enhancing Structured-Data Retrieval with GraphRAG: Soccer Data Case Study","created":"2024-09-26","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":"2511.17045","title":"RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis","created":"2025-11-21","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":"2602.22073","title":"AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting","created":"2026-02-25","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":"2607.18084","title":"WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"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":"2407.02370","title":"Investigating Event-Based Cameras for Video Frame Interpolation in Sports","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2506.17144","title":"Do We Need Large VLMs for Spotting Soccer Actions?","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2507.12617","title":"Predicting Soccer Penalty Kick Direction Using Human Action Recognition","created":"2025-07-16","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"},{"id":"2604.00057","title":"Towards Automatic Soccer Commentary Generation with Knowledge-Enhanced Visual Reasoning","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.05636","title":"Towards Athlete Fatigue Assessment from Association Football Videos","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.15736","title":"RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees","created":"2026-04-17","cited_by_count":1,"area":null}],"next_cursor":"100"}