{"list":"other","total":78,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2311.16493","title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","created":"2023-11-27","cited_by_count":667},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2409.06765","title":"gsplat: An Open-Source Library for Gaussian Splatting","created":"2024-09-10","cited_by_count":285},{"id":"2404.09591","title":"3D Gaussian Splatting as Markov Chain Monte Carlo","created":"2024-04-15","cited_by_count":217},{"id":"2402.14650","title":"GaussianPro: 3D Gaussian Splatting with Progressive Propagation","created":"2024-02-22","cited_by_count":200},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"1804.04527","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","created":"2018-04-12","cited_by_count":150},{"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":"2202.06934","title":"Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection","created":"2022-02-14","cited_by_count":105},{"id":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80},{"id":"2509.25164","title":"YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection","created":"2025-09-29","cited_by_count":79},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2211.03679","title":"Body Part-Based Representation Learning for Occluded Person Re-Identification","created":"2022-11-07","cited_by_count":64},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57},{"id":"1912.01326","title":"A Context-Aware Loss Function for Action Spotting in Soccer Videos","created":"2019-12-03","cited_by_count":56},{"id":"2411.14974","title":"3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes","created":"2024-11-22","cited_by_count":50},{"id":"2505.19175","title":"Triangle Splatting for Real-Time Radiance Field Rendering","created":"2025-05-25","cited_by_count":50},{"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":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","cited_by_count":40},{"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":"2205.10450","title":"Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors","created":"2022-05-20","cited_by_count":27},{"id":"2204.06859","title":"Semi-Supervised Training to Improve Player and Ball Detection in Soccer","created":"2022-04-14","cited_by_count":25},{"id":"2207.11709","title":"TVCalib: Camera Calibration for Sports Field Registration in Soccer","created":"2022-07-24","cited_by_count":22},{"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":"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},{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21},{"id":"2004.07209","title":"Using Player's Body-Orientation to Model Pass Feasibility in Soccer","created":"2020-04-15","cited_by_count":20},{"id":"2512.06818","title":"MeshSplatting: Differentiable Rendering with Opaque Meshes","created":"2025-12-07","cited_by_count":20},{"id":"2505.03735","title":"Multi-Agent System for Comprehensive Soccer Understanding","created":"2025-05-06","cited_by_count":18},{"id":"2204.04049","title":"Efficient tracking of team sport players with few game-specific annotations","created":"2022-04-08","cited_by_count":17},{"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},{"id":"2209.02250","title":"Spatio-Temporal Action Detection Under Large Motion","created":"2022-09-06","cited_by_count":14},{"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":"2501.02771","title":"WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation","created":"2025-01-06","cited_by_count":14},{"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":"2405.07354","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","created":"2024-05-12","cited_by_count":12},{"id":"2309.06285","title":"Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos","created":"2023-09-12","cited_by_count":10},{"id":"2512.11016","title":"SoccerMaster: A Vision Foundation Model for Soccer Understanding","created":"2025-12-11","cited_by_count":10},{"id":"2504.12021","title":"Action Anticipation from SoccerNet Football Video Broadcasts","created":"2025-04-16","cited_by_count":9},{"id":"2407.12483","title":"Towards AI-Powered Video Assistant Referee System (VARS) for Association Football","created":"2024-07-17","cited_by_count":8},{"id":"2010.11687","title":"PlenoptiCam v1.0: A light-field imaging framework","created":"2020-10-14","cited_by_count":7},{"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},{"id":"2402.09650","title":"Foul prediction with estimated poses from soccer broadcast video","created":"2024-02-15","cited_by_count":7},{"id":"2410.01304","title":"Deep learning for action spotting in association football videos","created":"2024-10-02","cited_by_count":7},{"id":"2410.07401","title":"Enhancing Soccer Camera Calibration Through Keypoint Exploitation","created":"2024-10-09","cited_by_count":7},{"id":"2402.00163","title":"Improving Object Detection Quality in Football Through Super-Resolution Techniques","created":"2024-01-31","cited_by_count":6},{"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},{"id":"2507.12905","title":"AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation Ability","created":"2025-07-17","cited_by_count":6},{"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},{"id":"2508.02493","title":"Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting","created":"2025-08-04","cited_by_count":5},{"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},{"id":"2504.10106","title":"SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene Understanding","created":"2025-04-14","cited_by_count":4},{"id":"2604.11786","title":"GenTac: Generative Modeling and Forecasting of Soccer Tactics","created":"2026-04-13","cited_by_count":3},{"id":"2504.20052","title":"Can Geometry Save Central Views for Sports Field Registration?","created":"2025-04-10","cited_by_count":2},{"id":"2602.22073","title":"AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting","created":"2026-02-25","cited_by_count":2},{"id":"2604.05636","title":"Towards Athlete Fatigue Assessment from Association Football Videos","created":"2026-04-07","cited_by_count":1}],"next_cursor":null}