{"total":131,"rows":[{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"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":"2306.08276","title":"TryOnDiffusion: A Tale of Two UNets","created":"2023-06-14","cited_by_count":141,"area":null},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131,"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":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112,"area":null},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107,"area":null},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2107.03332","title":"SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation","created":"2021-07-07","cited_by_count":68,"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":"2104.07300","title":"Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes","created":"2021-04-15","cited_by_count":65,"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":"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":"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":"2103.14843","title":"From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation","created":"2021-03-27","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":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42,"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":"2403.14852","title":"KeyPoint Relative Position Encoding for Face Recognition","created":"2024-03-21","cited_by_count":38,"area":null},{"id":"2103.06175","title":"Regressive Domain Adaptation for Unsupervised Keypoint Detection","created":"2021-03-10","cited_by_count":34,"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":"2107.02133","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","created":"2021-07-05","cited_by_count":33,"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":"2208.11547","title":"ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild","created":"2022-08-23","cited_by_count":23,"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":"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":"2104.03100","title":"HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap","created":"2021-04-07","cited_by_count":15,"area":null},{"id":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14,"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":"2301.00114","title":"Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions","created":"2022-12-31","cited_by_count":14,"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":"2504.12186","title":"CoMotion: Concurrent Multi-person 3D Motion","created":"2025-04-16","cited_by_count":13,"area":null},{"id":"2103.15573","title":"HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences","created":"2021-03-29","cited_by_count":12,"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":"2107.10327","title":"mmPose-NLP: A Natural Language Processing Approach to Precise Skeletal Pose Estimation using mmWave Radars","created":"2021-07-21","cited_by_count":11,"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":"2109.09090","title":"Low-resolution Human Pose Estimation","created":"2021-09-19","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":"2311.17105","title":"On the Calibration of Human Pose Estimation","created":"2023-11-28","cited_by_count":10,"area":null},{"id":"2210.00740","title":"Heatmap Distribution Matching for Human Pose Estimation","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2401.01730","title":"STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion","created":"2024-01-03","cited_by_count":9,"area":null},{"id":"2602.01661","title":"From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2210.00507","title":"Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifiers","created":"2022-10-02","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":"2303.11180","title":"Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2103.10180","title":"OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation","created":"2021-03-18","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":"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":"2206.10090","title":"KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences","created":"2022-06-21","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":"2109.10056","title":"Single Person Pose Estimation: A Survey","created":"2021-09-21","cited_by_count":4,"area":null},{"id":"2207.02425","title":"Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation","created":"2022-07-06","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":"2110.00523","title":"Mask or Non-Mask? Robust Face Mask Detector via Triplet-Consistency Representation Learning","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2110.15082","title":"SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae","created":"2021-10-28","cited_by_count":3,"area":null},{"id":"2202.02656","title":"A survey of top-down approaches for human pose estimation","created":"2022-02-05","cited_by_count":3,"area":null},{"id":"2204.07878","title":"3D Human Pose Estimation for Free-from and Moving Activities Using WiFi","created":"2022-04-16","cited_by_count":3,"area":null},{"id":"2209.02431","title":"DPIT: Dual-Pipeline Integrated Transformer for Human Pose Estimation","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2212.02163","title":"2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints","created":"2022-12-05","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":"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":"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":"2202.13197","title":"Relational Surrogate Loss Learning","created":"2022-02-26","cited_by_count":2,"area":null},{"id":"2206.02136","title":"LDRNet: Enabling Real-time Document Localization on Mobile Devices","created":"2022-06-05","cited_by_count":2,"area":null},{"id":"2301.07583","title":"A Survey of Advanced Computer Vision Techniques for Sports","created":"2023-01-18","cited_by_count":2,"area":null},{"id":"2305.14829","title":"Deakin RF-Sensing: Experiments on Correlated Knowledge Distillation for Monitoring Human Postures with Radios","created":"2023-05-24","cited_by_count":2,"area":"distill"},{"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":"2309.09515","title":"Sparse and Privacy-enhanced Representation for Human Pose Estimation","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2403.08650","title":"Data Augmentation in Human-Centric Vision","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2410.09583","title":"POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2412.01562","title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2507.16010","title":"FW-VTON: Flattening-and-Warping for Person-to-Person Virtual Try-on","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2103.08958","title":"Modulating Localization and Classification for Harmonized Object Detection","created":"2021-03-16","cited_by_count":1,"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":"2104.10414","title":"Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation","created":"2021-04-21","cited_by_count":1,"area":"distill"},{"id":"2105.10904","title":"Skeleton-aware multi-scale heatmap regression for 2D hand pose estimation","created":"2021-05-23","cited_by_count":1,"area":null},{"id":"2106.04269","title":"HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation","created":"2021-06-08","cited_by_count":1,"area":null},{"id":"2107.03215","title":"FasterPose: A Faster Simple Baseline for Human Pose Estimation","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2108.07199","title":"Real-time Human-Centric Segmentation for Complex Video Scenes","created":"2021-08-16","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":"2305.11101","title":"XFormer: Fast and Accurate Monocular 3D Body Capture","created":"2023-05-18","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":"2306.11529","title":"3D Keypoint Estimation Using Implicit Representation Learning","created":"2023-06-20","cited_by_count":1,"area":null},{"id":"2306.15114","title":"Transfer: Cross Modality Knowledge Transfer using Adversarial Networks -- A Study on Gesture Recognition","created":"2023-06-26","cited_by_count":1,"area":null},{"id":"2311.12829","title":"Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2406.15649","title":"Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipe","created":"2024-06-21","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":"2510.19170","title":"FootFormer: Estimating Stability from Visual Input","created":"2025-10-22","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}],"next_cursor":"100"}