{"total":131,"rows":[{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200,"area":null},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180,"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":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174,"area":null},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117,"area":null},{"id":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101,"area":null},{"id":"2403.19417","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","created":"2024-03-28","cited_by_count":82,"area":null},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74,"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":"2112.13715","title":"SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos","created":"2021-12-27","cited_by_count":64,"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":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","cited_by_count":49,"area":null},{"id":"2302.01593","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","created":"2023-02-03","cited_by_count":48,"area":null},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2305.08590","title":"NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation","created":"2023-05-15","cited_by_count":45,"area":null},{"id":"2201.07412","title":"Poseur: Direct Human Pose Regression with Transformers","created":"2022-01-19","cited_by_count":43,"area":null},{"id":"2207.10387","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","created":"2022-07-21","cited_by_count":36,"area":null},{"id":"2307.16687","title":"DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation","created":"2023-07-31","cited_by_count":36,"area":"diffusion"},{"id":"2207.14192","title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","created":"2022-07-28","cited_by_count":34,"area":null},{"id":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2210.12564","title":"HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar","created":"2022-10-22","cited_by_count":31,"area":null},{"id":"2411.19278","title":"OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration","created":"2024-11-28","cited_by_count":30,"area":null},{"id":"2203.08713","title":"DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation","created":"2022-03-16","cited_by_count":29,"area":null},{"id":"2210.07650","title":"DART: Articulated Hand Model with Diverse Accessories and Rich Textures","created":"2022-10-14","cited_by_count":25,"area":null},{"id":"2310.16447","title":"ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors","created":"2023-10-25","cited_by_count":24,"area":null},{"id":"2204.07370","title":"2D Human Pose Estimation: A Survey","created":"2022-04-15","cited_by_count":21,"area":null},{"id":"2308.12965","title":"POCO: 3D Pose and Shape Estimation with Confidence","created":"2023-08-24","cited_by_count":21,"area":null},{"id":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","cited_by_count":20,"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":"2407.08634","title":"RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2406.04659","title":"LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model","created":"2024-06-07","cited_by_count":17,"area":null},{"id":"2201.08613","title":"Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization","created":"2022-01-21","cited_by_count":14,"area":null},{"id":"2212.07855","title":"QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query","created":"2022-12-15","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":"2407.11321","title":"TCFormer: Visual Recognition via Token Clustering Transformer","created":"2024-07-16","cited_by_count":12,"area":null},{"id":"2110.08825","title":"Localization with Sampling-Argmax","created":"2021-10-17","cited_by_count":11,"area":null},{"id":"2303.04346","title":"Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module","created":"2023-03-08","cited_by_count":10,"area":null},{"id":"2311.17105","title":"On the Calibration of Human Pose Estimation","created":"2023-11-28","cited_by_count":10,"area":null},{"id":"2403.19926","title":"Video-Based Human Pose Regression via Decoupled Space-Time Aggregation","created":"2024-03-29","cited_by_count":10,"area":null},{"id":"2407.05238","title":"P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds","created":"2024-07-07","cited_by_count":10,"area":null},{"id":"2512.10881","title":"MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2203.07697","title":"Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation","created":"2022-03-15","cited_by_count":9,"area":null},{"id":"2210.00740","title":"Heatmap Distribution Matching for Human Pose Estimation","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2303.01743","title":"A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation","created":"2023-03-03","cited_by_count":9,"area":null},{"id":"2412.02254","title":"ProbPose: A Probabilistic Approach to 2D Human Pose Estimation","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2407.19675","title":"Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment","created":"2024-07-29","cited_by_count":8,"area":null},{"id":"2307.16765","title":"Lightweight Super-Resolution Head for Human Pose Estimation","created":"2023-07-31","cited_by_count":7,"area":null},{"id":"2403.13647","title":"Meta-Point Learning and Refining for Category-Agnostic Pose Estimation","created":"2024-03-20","cited_by_count":7,"area":null},{"id":"2503.05122","title":"EDM: Efficient Deep Feature Matching","created":"2025-03-07","cited_by_count":7,"area":null},{"id":"2601.12882","title":"YOLO26: An Analysis of NMS-Free End to End Framework for Real-Time Object Detection","created":"2026-01-19","cited_by_count":7,"area":null},{"id":"2208.11960","title":"FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2211.07501","title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2211.11983","title":"Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2303.17216","title":"Few-shot Geometry-Aware Keypoint Localization","created":"2023-03-30","cited_by_count":6,"area":null},{"id":"2310.13039","title":"Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2404.14634","title":"UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues","created":"2024-04-23","cited_by_count":6,"area":null},{"id":"2305.10465","title":"Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2306.17074","title":"Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation","created":"2023-06-29","cited_by_count":5,"area":"diffusion"},{"id":"2310.15624","title":"GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2403.09063","title":"Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2405.15939","title":"Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2407.12307","title":"Weakly-Supervised 3D Hand Reconstruction with Knowledge Prior and Uncertainty Guidance","created":"2024-07-17","cited_by_count":5,"area":null},{"id":"2408.02263","title":"VoxelTrack: Exploring Voxel Representation for 3D Point Cloud Object Tracking","created":"2024-08-05","cited_by_count":5,"area":null},{"id":"2410.17136","title":"AlphaChimp: Tracking and Behavior Recognition of Chimpanzees","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2411.01846","title":"KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension","created":"2024-11-04","cited_by_count":5,"area":"mllm"},{"id":"2412.13058","title":"CondiMen: Conditional Multi-Person Mesh Recovery","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2505.02481","title":"Finger Pose Estimation for Under-screen Fingerprint Sensor","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2302.04589","title":"MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection","created":"2023-02-09","cited_by_count":4,"area":null},{"id":"2509.11453","title":"Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking","created":"2025-09-14","cited_by_count":4,"area":null},{"id":"2301.10431","title":"Bias-Compensated Integral Regression for Human Pose Estimation","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2309.02185","title":"BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye View","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2406.12219","title":"PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2508.17239","title":"PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation","created":"2025-08-24","cited_by_count":3,"area":null},{"id":"2206.13577","title":"A View Independent Classification Framework for Yoga Postures","created":"2022-06-27","cited_by_count":2,"area":null},{"id":"2404.10985","title":"Pixel-Wise Symbol Spotting via Progressive Points Location for Parsing CAD Images","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2405.17016","title":"$\\text{Di}^2\\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation","created":"2024-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2407.02926","title":"Explainable vertebral fracture analysis with uncertainty estimation using differentiable rule-based classification","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2503.21140","title":"Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2505.02287","title":"Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation","created":"2025-05-04","cited_by_count":2,"area":null},{"id":"2511.08387","title":"RAPTR: Radar-based 3D Pose Estimation using Transformer","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2609.07738","title":"TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking","created":"2026-09-07","cited_by_count":2,"area":null},{"id":"2302.08751","title":"MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2305.17283","title":"Sharpened Lazy Incremental Quasi-Newton Method","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2306.03538","title":"SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2312.10195","title":"SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data Augmentation","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2403.12109","title":"GCAM: Gaussian and causal-attention model of food fine-grained recognition","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2404.03518","title":"SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation","created":"2024-04-04","cited_by_count":1,"area":"distill"},{"id":"2406.19726","title":"EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans","created":"2024-06-28","cited_by_count":1,"area":null},{"id":"2408.01688","title":"SiamMo: Siamese Motion-Centric 3D Object Tracking","created":"2024-08-03","cited_by_count":1,"area":null},{"id":"2411.18944","title":"Waterfall Transformer for Multi-person Pose Estimation","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2412.13010","title":"Measurement of Medial Elbow Joint Space using Landmark Detection","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2501.08038","title":"Robust Low-Light Human Pose Estimation through Illumination-Texture Modulation","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2502.11179","title":"RT-DEMT: A hybrid real-time acupoint detection model combining mamba and transformer","created":"2025-02-16","cited_by_count":1,"area":"ssm"},{"id":"2504.10190","title":"Differentially Private 2D Human Pose Estimation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2508.08783","title":"DiffPose-Animal: A Language-Conditioned Diffusion Framework for Animal Pose Estimation","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.16973","title":"Balanced Sharpness-Aware Minimization for Imbalanced Regression","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2511.13208","title":"End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2303.06800","title":"Object-Centric Multi-Task Learning for Human Instances","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2303.14838","title":"Lightweight Estimation of Hand Mesh and Biomechanically Feasible Kinematic Parameters","created":"2023-03-26","cited_by_count":0,"area":null}],"next_cursor":"100"}