{"total":117,"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":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142,"area":null},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112,"area":null},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"area":null},{"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,"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":"2111.04076","title":"Direct Multi-view Multi-person 3D Pose Estimation","created":"2021-11-07","cited_by_count":64,"area":null},{"id":"2211.03679","title":"Body Part-Based Representation Learning for Occluded Person Re-Identification","created":"2022-11-07","cited_by_count":64,"area":null},{"id":"2103.02440","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","created":"2021-03-03","cited_by_count":55,"area":null},{"id":"2103.07254","title":"Deep Dual Consecutive Network for Human Pose Estimation","created":"2021-03-12","cited_by_count":51,"area":null},{"id":"2104.11536","title":"Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective","created":"2021-04-23","cited_by_count":50,"area":null},{"id":"2105.06152","title":"When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks","created":"2021-05-13","cited_by_count":41,"area":null},{"id":"2108.02452","title":"VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild","created":"2021-08-05","cited_by_count":39,"area":null},{"id":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34,"area":null},{"id":"2103.04570","title":"Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing","created":"2021-03-08","cited_by_count":31,"area":null},{"id":"2101.11223","title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","created":"2021-01-27","cited_by_count":30,"area":null},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30,"area":null},{"id":"2308.07313","title":"Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation","created":"2023-08-14","cited_by_count":26,"area":null},{"id":"2203.15227","title":"Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation","created":"2022-03-29","cited_by_count":24,"area":null},{"id":"2310.11016","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","created":"2023-10-17","cited_by_count":23,"area":null},{"id":"2101.02471","title":"PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation","created":"2021-01-07","cited_by_count":22,"area":null},{"id":"2204.07370","title":"2D Human Pose Estimation: A Survey","created":"2022-04-15","cited_by_count":21,"area":null},{"id":"2404.02041","title":"SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation","created":"2024-04-02","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":"2110.05132","title":"The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation","created":"2021-10-11","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":"2303.08475","title":"Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2109.12946","title":"Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks","created":"2021-09-27","cited_by_count":15,"area":null},{"id":"2109.03622","title":"Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation","created":"2021-09-08","cited_by_count":14,"area":null},{"id":"2207.03714","title":"Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation","created":"2022-07-08","cited_by_count":14,"area":null},{"id":"2208.07755","title":"PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation","created":"2022-08-16","cited_by_count":14,"area":null},{"id":"2107.08982","title":"InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2205.00748","title":"Dual networks based 3D Multi-Person Pose Estimation from Monocular Video","created":"2022-05-02","cited_by_count":13,"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":"2308.13954","title":"Prior-guided Source-free Domain Adaptation for Human Pose Estimation","created":"2023-08-26","cited_by_count":13,"area":null},{"id":"2207.14452","title":"Deep Learning-based Occluded Person Re-identification: A Survey","created":"2022-07-29","cited_by_count":12,"area":null},{"id":"2209.13948","title":"Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2407.18907","title":"SHIC: Shape-Image Correspondences with no Keypoint Supervision","created":"2024-07-26","cited_by_count":12,"area":null},{"id":"2112.00627","title":"DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes","created":"2021-12-01","cited_by_count":11,"area":null},{"id":"2202.09947","title":"Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation","created":"2022-02-21","cited_by_count":10,"area":null},{"id":"2208.00090","title":"Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation","created":"2022-07-29","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":"2109.09166","title":"Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition","created":"2021-09-19","cited_by_count":9,"area":null},{"id":"2207.11341","title":"Dynamic Graph Reasoning for Multi-person 3D Pose Estimation","created":"2022-07-22","cited_by_count":9,"area":null},{"id":"2210.06028","title":"VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation","created":"2022-10-12","cited_by_count":9,"area":null},{"id":"2110.00988","title":"Keypoint Communities","created":"2021-10-03","cited_by_count":8,"area":null},{"id":"2106.00980","title":"End-to-End Hierarchical Relation Extraction for Generic Form Understanding","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2108.11801","title":"Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2207.10952","title":"Vision-based Human Fall Detection Systems using Deep Learning: A Review","created":"2022-07-22","cited_by_count":7,"area":null},{"id":"2308.07743","title":"ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2112.13635","title":"AdaptivePose: Human Parts as Adaptive Points","created":"2021-12-27","cited_by_count":6,"area":null},{"id":"2201.01087","title":"Learning Quality-aware Representation for Multi-person Pose Regression","created":"2022-01-04","cited_by_count":6,"area":null},{"id":"2207.02976","title":"Semi-supervised Human Pose Estimation in Art-historical Images","created":"2022-07-06","cited_by_count":6,"area":null},{"id":"2210.04014","title":"AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regression","created":"2022-10-08","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":"2311.11888","title":"SniffyArt: The Dataset of Smelling Persons","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2410.20508","title":"Referring Human Pose and Mask Estimation in the Wild","created":"2024-10-27","cited_by_count":6,"area":null},{"id":"2104.02486","title":"SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation","created":"2021-04-06","cited_by_count":5,"area":null},{"id":"2108.11826","title":"Fast and Flexible Human Pose Estimation with HyperPose","created":"2021-08-26","cited_by_count":5,"area":null},{"id":"2112.04212","title":"Do Pedestrians Pay Attention? Eye Contact Detection in the Wild","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2204.11511","title":"A Spatio-Temporal Multilayer Perceptron for Gesture Recognition","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2208.11975","title":"Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2212.09298","title":"From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2305.13765","title":"Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2507.22742","title":"Social-Pose: Enhancing Trajectory Prediction with Human Body Pose","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2307.11934","title":"LAMP: Leveraging Language Prompts for Multi-person Pose Estimation","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2310.18953","title":"TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2406.19290","title":"Human Modelling and Pose Estimation Overview","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2107.02675","title":"Real-time Pose Estimation from Images for Multiple Humanoid Robots","created":"2021-07-06","cited_by_count":3,"area":null},{"id":"2112.10716","title":"BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations","created":"2021-12-20","cited_by_count":3,"area":null},{"id":"2310.18920","title":"Improving Multi-Person Pose Tracking with A Confidence Network","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2411.03086","title":"HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2507.22438","title":"From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras","created":"2025-07-30","cited_by_count":3,"area":null},{"id":"2510.21654","title":"Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2111.12892","title":"Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2202.00753","title":"ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2202.09550","title":"Student Dangerous Behavior Detection in School","created":"2022-02-19","cited_by_count":2,"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":"2212.08731","title":"Multi-person 3D pose estimation from unlabelled data","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2307.01004","title":"Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approach","created":"2023-07-03","cited_by_count":2,"area":null},{"id":"2309.14072","title":"BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2404.06246","title":"GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields","created":"2024-04-09","cited_by_count":2,"area":null},{"id":"2404.14025","title":"DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation","created":"2024-04-22","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":"2104.02385","title":"Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping","created":"2021-04-06","cited_by_count":1,"area":null},{"id":"2204.01263","title":"Direct Dense Pose Estimation","created":"2022-04-04","cited_by_count":1,"area":null},{"id":"2205.12619","title":"Location-free Human Pose Estimation","created":"2022-05-25","cited_by_count":1,"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":"2407.03268","title":"For a semiotic AI: Bridging computer vision and visual semiotics for computational observation of large scale facial image archives","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2407.10220","title":"PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2410.04889","title":"D-PoSE: Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2504.19032","title":"VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation","created":"2025-04-26","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":"2102.07318","title":"A Global to Local Double Embedding Method for Multi-person Pose Estimation","created":"2021-02-15","cited_by_count":0,"area":null},{"id":"2107.03098","title":"Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation","created":"2021-07-07","cited_by_count":0,"area":null},{"id":"2110.10734","title":"Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation","created":"2021-10-20","cited_by_count":0,"area":null},{"id":"2207.06847","title":"Covy: An AI-powered Robot with a Compound Vision System for Detecting Breaches in Social Distancing","created":"2022-07-14","cited_by_count":0,"area":null},{"id":"2209.15404","title":"Entropy-driven Unsupervised Keypoint Representation Learning in Videos","created":"2022-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}