{"total":412,"rows":[{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350,"area":null},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227,"area":null},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206,"area":null},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166,"area":null},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164,"area":null},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155,"area":null},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149,"area":null},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142,"area":null},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130,"area":null},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"area":null},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106,"area":null},{"id":"2402.14654","title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","created":"2024-02-22","cited_by_count":101,"area":null},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95,"area":null},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2509.14055","title":"Wan-Animate: Unified Character Animation and Replacement with Holistic Replication","created":"2025-09-17","cited_by_count":80,"area":null},{"id":"2303.02760","title":"Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes","created":"2023-03-05","cited_by_count":68,"area":null},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68,"area":null},{"id":"2503.21860","title":"ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65,"area":null},{"id":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65,"area":null},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61,"area":null},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56,"area":null},{"id":"2305.15272","title":"ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers","created":"2023-05-24","cited_by_count":56,"area":null},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54,"area":null},{"id":"2404.00299","title":"HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment","created":"2024-03-30","cited_by_count":53,"area":null},{"id":"2312.07495","title":"Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection","created":"2023-12-12","cited_by_count":47,"area":null},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","cited_by_count":46,"area":null},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2402.03526","title":"nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Model","created":"2024-02-05","cited_by_count":45,"area":null},{"id":"2304.08114","title":"ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection","created":"2023-04-17","cited_by_count":41,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37,"area":null},{"id":"2411.14280","title":"EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild","created":"2024-11-21","cited_by_count":36,"area":null},{"id":"2310.13768","title":"PACE: Human and Camera Motion Estimation from in-the-wild Videos","created":"2023-10-20","cited_by_count":34,"area":null},{"id":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","cited_by_count":33,"area":null},{"id":"2310.20695","title":"HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception","created":"2023-10-31","cited_by_count":33,"area":null},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33,"area":null},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31,"area":null},{"id":"2310.20436","title":"SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark","created":"2023-10-31","cited_by_count":29,"area":null},{"id":"2501.02158","title":"Joint Optimization for 4D Human-Scene Reconstruction in the Wild","created":"2025-01-04","cited_by_count":29,"area":null},{"id":"2403.14625","title":"LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors","created":"2024-03-21","cited_by_count":27,"area":null},{"id":"2206.11752","title":"CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose","created":"2022-06-23","cited_by_count":25,"area":null},{"id":"2307.00997","title":"RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation","created":"2023-07-03","cited_by_count":25,"area":null},{"id":"2308.10305","title":"Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video","created":"2023-08-20","cited_by_count":25,"area":null},{"id":"2404.19722","title":"PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios","created":"2024-04-30","cited_by_count":24,"area":null},{"id":"2211.10927","title":"GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds","created":"2022-11-20","cited_by_count":23,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2410.03311","title":"Scaling Large Motion Models with Million-Level Human Motions","created":"2024-10-04","cited_by_count":22,"area":null},{"id":"2503.21751","title":"Reconstructing Humans with a Biomechanically Accurate Skeleton","created":"2025-03-27","cited_by_count":22,"area":null},{"id":"2310.08530","title":"X-Pose: Detecting Any Keypoints","created":"2023-10-12","cited_by_count":21,"area":null},{"id":"2308.13872","title":"Vision-Based Human Pose Estimation via Deep Learning: A Survey","created":"2023-08-26","cited_by_count":20,"area":null},{"id":"2412.11149","title":"A Comprehensive Survey of Action Quality Assessment: Method and Benchmark","created":"2024-12-15","cited_by_count":20,"area":null},{"id":"2306.17000","title":"MotionTrack: End-to-End Transformer-based Multi-Object Tracing with LiDAR-Camera Fusion","created":"2023-06-29","cited_by_count":19,"area":null},{"id":"2301.11326","title":"Unsupervised Volumetric Animation","created":"2023-01-26","cited_by_count":18,"area":null},{"id":"2308.15844","title":"Reconstructing Groups of People with Hypergraph Relational Reasoning","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2301.03561","title":"Ancilia: Scalable Intelligent Video Surveillance for the Artificial Intelligence of Things","created":"2023-01-09","cited_by_count":17,"area":null},{"id":"2303.08450","title":"PoseRAC: Pose Saliency Transformer for Repetitive Action Counting","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2311.17891","title":"A Graph-Based Approach for Category-Agnostic Pose Estimation","created":"2023-11-29","cited_by_count":17,"area":null},{"id":"2404.12347","title":"AniClipart: Clipart Animation with Text-to-Video Priors","created":"2024-04-18","cited_by_count":17,"area":null},{"id":"2404.14410","title":"Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2406.10447","title":"The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences","created":"2024-06-14","cited_by_count":17,"area":null},{"id":"2508.01126","title":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","created":"2025-08-02","cited_by_count":17,"area":null},{"id":"2210.13853","title":"THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2304.11584","title":"OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking","created":"2023-04-23","cited_by_count":16,"area":null},{"id":"2502.11534","title":"SurgPose: a Dataset for Articulated Robotic Surgical Tool Pose Estimation and Tracking","created":"2025-02-17","cited_by_count":16,"area":null},{"id":"2403.12778","title":"ViTGaze: Gaze Following with Interaction Features in Vision Transformers","created":"2024-03-19","cited_by_count":15,"area":null},{"id":"2404.12440","title":"Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds","created":"2024-04-18","cited_by_count":15,"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":"2503.07499","title":"AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2505.11152","title":"Learning Dense Hand Contact Estimation from Imbalanced Data","created":"2025-05-16","cited_by_count":14,"area":null},{"id":"2510.11649","title":"PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image","created":"2025-10-13","cited_by_count":14,"area":null},{"id":"2304.04437","title":"Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration","created":"2023-04-10","cited_by_count":13,"area":null},{"id":"2306.07879","title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","created":"2023-06-13","cited_by_count":13,"area":null},{"id":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","cited_by_count":13,"area":null},{"id":"2303.02455","title":"DistilPose: Tokenized Pose Regression with Heatmap Distillation","created":"2023-03-04","cited_by_count":12,"area":null},{"id":"2306.05135","title":"Does Image Anonymization Impact Computer Vision Training?","created":"2023-06-08","cited_by_count":12,"area":null},{"id":"2308.10174","title":"Neural Interactive Keypoint Detection","created":"2023-08-20","cited_by_count":12,"area":null},{"id":"2308.15316","title":"3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking","created":"2023-08-29","cited_by_count":12,"area":null},{"id":"2309.16524","title":"HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs","created":"2023-09-28","cited_by_count":12,"area":null},{"id":"2311.11971","title":"LiDAR-HMR: 3D Human Mesh Recovery from LiDAR","created":"2023-11-20","cited_by_count":12,"area":null},{"id":"2311.17754","title":"Cinematic Behavior Transfer via NeRF-based Differentiable Filming","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2406.01595","title":"MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild","created":"2024-06-03","cited_by_count":12,"area":null},{"id":"2406.11933","title":"Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2407.11321","title":"TCFormer: Visual Recognition via Token Clustering Transformer","created":"2024-07-16","cited_by_count":12,"area":null},{"id":"2412.08101","title":"Generative Zoo","created":"2024-12-11","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":"2308.00628","title":"Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes","created":"2023-08-01","cited_by_count":11,"area":null},{"id":"2308.10623","title":"GaitPT: Skeletons Are All You Need For Gait Recognition","created":"2023-08-21","cited_by_count":11,"area":null},{"id":"2308.16876","title":"SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation","created":"2023-08-31","cited_by_count":11,"area":null},{"id":"2311.03312","title":"A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation","created":"2023-11-06","cited_by_count":11,"area":null},{"id":"2405.13896","title":"A General Framework for Jersey Number Recognition in Sports Video","created":"2024-05-22","cited_by_count":11,"area":null},{"id":"2411.18808","title":"Lifting Motion to the 3D World via 2D Diffusion","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2311.17105","title":"On the Calibration of Human Pose Estimation","created":"2023-11-28","cited_by_count":10,"area":null}],"next_cursor":"100"}