{"total":305,"rows":[{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456,"area":null},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"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":"2107.12746","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","created":"2021-07-27","cited_by_count":152,"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":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112,"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":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"area":null},{"id":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83,"area":"diffusion"},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74,"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":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65,"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":"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":"2108.02092","title":"Online Knowledge Distillation for Efficient Pose Estimation","created":"2021-08-04","cited_by_count":55,"area":"distill"},{"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":"2206.13732","title":"A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges","created":"2022-06-28","cited_by_count":45,"area":null},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2103.15263","title":"Zero-shot Adversarial Quantization","created":"2021-03-29","cited_by_count":44,"area":null},{"id":"2201.07412","title":"Poseur: Direct Human Pose Regression with Transformers","created":"2022-01-19","cited_by_count":43,"area":null},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42,"area":null},{"id":"2312.14233","title":"VCoder: Versatile Vision Encoders for Multimodal Large Language Models","created":"2023-12-21","cited_by_count":42,"area":"mllm"},{"id":"2405.16273","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","created":"2024-05-25","cited_by_count":38,"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":"2109.05721","title":"ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment","created":"2021-09-13","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":"2209.02399","title":"SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition","created":"2022-09-01","cited_by_count":29,"area":null},{"id":"2211.05641","title":"Regression as Classification: Influence of Task Formulation on Neural Network Features","created":"2022-11-10","cited_by_count":29,"area":null},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28,"area":"mllm"},{"id":"2106.11346","title":"GAIA: A Transfer Learning System of Object Detection that Fits Your Needs","created":"2021-06-21","cited_by_count":27,"area":null},{"id":"2112.06183","title":"Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species","created":"2021-12-12","cited_by_count":27,"area":null},{"id":"2209.08194","title":"PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation","created":"2022-09-16","cited_by_count":27,"area":null},{"id":"2303.15410","title":"Human Pose Estimation in Extremely Low-Light Conditions","created":"2023-03-27","cited_by_count":27,"area":null},{"id":"2105.04154","title":"Unsupervised Human Pose Estimation through Transforming Shape Templates","created":"2021-05-10","cited_by_count":26,"area":null},{"id":"2206.04511","title":"Efficient Human Pose Estimation via 3D Event Point Cloud","created":"2022-06-09","cited_by_count":25,"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":"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":"2105.07140","title":"NeuroGen: activation optimized image synthesis for discovery neuroscience","created":"2021-05-15","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":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","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":"2303.12741","title":"A Method for Animating Children's Drawings of the Human Figure","created":"2023-03-07","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":"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":"2406.04659","title":"LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model","created":"2024-06-07","cited_by_count":17,"area":null},{"id":"2204.01565","title":"HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE","created":"2022-04-04","cited_by_count":16,"area":null},{"id":"2104.08383","title":"Optimal Pose and Shape Estimation for Category-level 3D Object Perception","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2405.12070","title":"AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements","created":"2024-05-20","cited_by_count":15,"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":"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":"2109.07353","title":"Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos","created":"2021-09-15","cited_by_count":13,"area":null},{"id":"2308.00519","title":"Markerless human pose estimation for biomedical applications: a survey","created":"2023-08-01","cited_by_count":13,"area":null},{"id":"2410.10167","title":"X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2103.03663","title":"Real-time RGBD-based Extended Body Pose Estimation","created":"2021-03-05","cited_by_count":12,"area":null},{"id":"2104.01703","title":"FixMyPose: Pose Correctional Captioning and Retrieval","created":"2021-04-04","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":"2309.16964","title":"AdaPose: Towards Cross-Site Device-Free Human Pose Estimation with Commodity WiFi","created":"2023-09-29","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":"2101.07719","title":"Deep Feedback Inverse Problem Solver","created":"2021-01-19","cited_by_count":11,"area":null},{"id":"2101.08967","title":"Human Interaction Recognition Framework based on Interacting Body Part Attention","created":"2021-01-22","cited_by_count":11,"area":null},{"id":"2312.10758","title":"SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation","created":"2023-12-17","cited_by_count":11,"area":null},{"id":"2406.18537","title":"AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale","created":"2024-05-16","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":"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":"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":"2108.00249","title":"SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation","created":"2021-07-31","cited_by_count":9,"area":null},{"id":"2201.07384","title":"Swin-Pose: Swin Transformer Based Human Pose Estimation","created":"2022-01-19","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":"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":"2308.02177","title":"Scene-aware Human Pose Generation using Transformer","created":"2023-08-04","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":"2510.07723","title":"SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2103.15534","title":"An Adversarial Human Pose Estimation Network Injected with Graph Structure","created":"2021-03-29","cited_by_count":8,"area":null},{"id":"2104.04899","title":"Location-Sensitive Visual Recognition with Cross-IOU Loss","created":"2021-04-11","cited_by_count":8,"area":null},{"id":"2110.00988","title":"Keypoint Communities","created":"2021-10-03","cited_by_count":8,"area":null},{"id":"2208.09872","title":"Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks","created":"2022-08-21","cited_by_count":8,"area":null},{"id":"2304.02349","title":"Self-supervised 3D Human Pose Estimation from a Single Image","created":"2023-04-05","cited_by_count":8,"area":null},{"id":"2403.17893","title":"A Survey on 3D Egocentric Human Pose Estimation","created":"2024-03-26","cited_by_count":8,"area":null},{"id":"2408.05436","title":"A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities","created":"2024-08-10","cited_by_count":8,"area":null},{"id":"2409.19899","title":"OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2107.09086","title":"DPNNet-2.0 Part I: Finding hidden planets from simulated images of protoplanetary disk gaps","created":"2021-07-19","cited_by_count":7,"area":null},{"id":"2204.05864","title":"Semantic keypoint-based pose estimation from single RGB frames","created":"2022-04-12","cited_by_count":7,"area":null},{"id":"2206.12498","title":"Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints","created":"2022-06-24","cited_by_count":7,"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":"2407.13437","title":"FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions","created":"2024-07-18","cited_by_count":7,"area":null},{"id":"2407.16560","title":"COALA: A Practical and Vision-Centric Federated Learning Platform","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2408.02285","title":"Joint-Motion Mutual Learning for Pose Estimation in Videos","created":"2024-08-05","cited_by_count":7,"area":null},{"id":"2103.03170","title":"Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions","created":"2021-03-04","cited_by_count":6,"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":"2109.09533","title":"Modeling Annotation Uncertainty with Gaussian Heatmaps in Landmark Localization","created":"2021-09-20","cited_by_count":6,"area":null},{"id":"2112.02763","title":"MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samples","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2112.05597","title":"Marvin: an Innovative Omni-Directional Robotic Assistant for Domestic Environments","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2210.11179","title":"Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions","created":"2022-10-20","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}],"next_cursor":"100"}