{"list":"other","total":69,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2312.07843","title":"Foundation Models in Robotics: Applications, Challenges, and the Future","created":"2023-12-13","cited_by_count":216},{"id":"1804.04527","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","created":"2018-04-12","cited_by_count":150},{"id":"2303.10895","title":"Leapfrog Diffusion Model for Stochastic Trajectory Prediction","created":"2023-03-20","cited_by_count":132},{"id":"2011.13367","title":"SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos","created":"2020-11-26","cited_by_count":131},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107},{"id":"1607.02643","title":"Hierarchical Deep Temporal Models for Group Activity Recognition","created":"2016-07-09","cited_by_count":89},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84},{"id":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80},{"id":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57},{"id":"2402.01105","title":"A Survey for Foundation Models in Autonomous Driving","created":"2024-02-02","cited_by_count":52},{"id":"2310.10553","title":"TacticAI: an AI assistant for football tactics","created":"2023-10-16","cited_by_count":44},{"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},{"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},{"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},{"id":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37},{"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},{"id":"2210.02365","title":"SoccerNet 2022 Challenges Results","created":"2022-10-05","cited_by_count":28},{"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},{"id":"2204.06859","title":"Semi-Supervised Training to Improve Player and Ball Detection in Soccer","created":"2022-04-14","cited_by_count":25},{"id":"2410.08474","title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","created":"2024-10-11","cited_by_count":24},{"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},{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21},{"id":"1804.03247","title":"Fine-grained Activity Recognition in Baseball Videos","created":"2018-04-09","cited_by_count":20},{"id":"2309.06006","title":"SoccerNet 2023 Challenges Results","created":"2023-09-12","cited_by_count":20},{"id":"2505.03735","title":"Multi-Agent System for Comprehensive Soccer Understanding","created":"2025-05-06","cited_by_count":18},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17},{"id":"2402.15862","title":"SportQA: A Benchmark for Sports Understanding in Large Language Models","created":"2024-02-24","cited_by_count":15},{"id":"2404.08401","title":"PnLCalib: Sports Field Registration via Points and Lines Optimization","created":"2024-04-12","cited_by_count":14},{"id":"2404.09807","title":"A Universal Protocol to Benchmark Camera Calibration for Sports","created":"2024-04-15","cited_by_count":14},{"id":"2208.04897","title":"Sports Video Analysis on Large-Scale Data","created":"2022-08-09","cited_by_count":13},{"id":"2401.09942","title":"Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking","created":"2024-01-18","cited_by_count":13},{"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},{"id":"2405.13896","title":"A General Framework for Jersey Number Recognition in Sports Video","created":"2024-05-22","cited_by_count":11},{"id":"2309.06285","title":"Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos","created":"2023-09-12","cited_by_count":10},{"id":"2504.20041","title":"Learning Streaming Video Representation via Multitask Training","created":"2025-04-28","cited_by_count":10},{"id":"2409.10587","title":"SoccerNet 2024 Challenges Results","created":"2024-09-16","cited_by_count":8},{"id":"2410.07401","title":"Enhancing Soccer Camera Calibration Through Keypoint Exploitation","created":"2024-10-09","cited_by_count":7},{"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},{"id":"2505.23617","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","created":"2025-05-29","cited_by_count":7},{"id":"2507.20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","created":"2025-07-27","cited_by_count":7},{"id":"2412.01721","title":"BroadTrack: Broadcast Camera Tracking for Soccer","created":"2024-12-02","cited_by_count":5},{"id":"2508.19182","title":"SoccerNet 2025 Challenges Results","created":"2025-08-26","cited_by_count":4},{"id":"2511.13326","title":"TacEleven: generative tactic discovery for football open play","created":"2025-11-17","cited_by_count":4},{"id":"2504.06357","title":"From Broadcast to Minimap: Achieving State-of-the-Art SoccerNet Game State Reconstruction","created":"2025-04-08","cited_by_count":1}],"next_cursor":null}