mlsanityData to 7 Oct 2026

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time

arXiv 2211.03375 ↗First posted 7 Nov 2022cs.CVcited by 199

Not on the map. Why?

Abstract (arXiv)

Accurate whole-body multi-person pose estimation and tracking is an important yet challenging topic in computer vision. To capture the subtle actions of humans for complex behavior analysis, whole-body pose estimation including the face, body, hand and foot is essential over conventional body-only pose estimation. In this paper, we present AlphaPose, a system that can perform accurate whole-body pose estimation and tracking jointly while running in realtime. To this end, we propose several new techniques: Symmetric Integral Keypoint Regression (SIKR) for fast and fine localization, Parametric Pose Non-Maximum-Suppression (P-NMS) for eliminating redundant human detections and Pose Aware Identity Embedding for jointly pose estimation and tracking. During training, we resort to Part-Guided Proposal Generator (PGPG) and multi-domain knowledge distillation to further improve the accuracy. Our method is able to localize whole-body keypoints accurately and tracks humans simultaneously given inaccurate bounding boxes and redundant detections. We show a significant improvement over current state-of-the-art methods in both speed and accuracy on COCO-wholebody, COCO, PoseTrack, and our proposed Halpe-FullBody pose estimation dataset. Our model, source codes and dataset are made publicly available at https://github.com/MVIG-SJTU/AlphaPose.

Key facts. Cited by 199 papers in the map (data through 7 Oct 2026). Builds on 71 of its 90 references that are in the map. First posted on arXiv 7 Nov 2022.

Builds on

71 of 90 references.

References · 71

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2018YOLOv3: An Incremental Improvementcited by 2,652
  7. 2017Deformable Convolutional Networkscited by 1,481
  8. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  11. 2019Objects as Pointscited by 1,172
  12. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
38 more
  1. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  2. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  3. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  4. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  5. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  6. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  7. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 380
  8. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  9. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  10. 2016Convolutional Pose Machinescited by 325
  11. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
  12. 2019Towards Real-Time Multi-Object Trackingcited by 311
  13. 2016LIFT: Learned Invariant Feature Transformcited by 305
  14. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  15. 2017Integral Human Pose Regressioncited by 255
  16. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  17. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 244
  18. 2017Learning to Detect Human-Object Interactionscited by 238
  19. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  20. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  21. 2015MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systemscited by 195
  22. 2020Whole-Body Human Pose Estimation in the Wildcited by 178
  23. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  24. 2017Understanding Convolution for Semantic Segmentationcited by 168
  25. 2018Look at Boundary: A Boundary-Aware Face Alignment Algorithmcited by 137
  26. 2017On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learningcited by 136
  27. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  28. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  29. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  30. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  31. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  32. 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
  33. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  34. 2019Single-Stage Multi-Person Pose Machinescited by 95
  35. 2018Pose Flow: Efficient Online Pose Trackingcited by 80
  36. 2020TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Modelcited by 70
  37. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  38. 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 62; 2024: 55; 2025: 47; 2026: 31.

199 papers.

Sort:

By area:

  1. 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 307
  2. 2023Reconstructing Hands in 3D with Transformerscited by 298
  3. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  4. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
  5. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  6. 2023UniHCP: A Unified Model for Human-Centric Perceptionscited by 59
  7. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  8. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 48
  9. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  10. 2023GenZI: Zero-Shot 3D Human-Scene Interaction Generationcited by 40
  11. 2023GPGait: Generalized Pose-based Gait Recognitioncited by 39
  12. 2023AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perceptioncited by 39
38 more
  1. 2023HumanBench: Towards General Human-centric Perception with Projector Assisted Pretrainingcited by 38
  2. 2023MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusioncited by 37
  3. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  4. 2025From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humanscited by 27
  5. 2023MANUS: Markerless Grasp Capture using Articulated 3D Gaussianscited by 26
  6. 2024A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insightscited by 24
  7. 2023Robots That Can See: Leveraging Human Pose for Trajectory Predictioncited by 22
  8. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  9. 2023A Method for Animating Children's Drawings of the Human Figurecited by 20
  10. 2024SignCLIP: Connecting Text and Sign Language by Contrastive Learningcited by 20
  11. 2023From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understandingcited by 19
  12. 2024Systemic Biases in Sign Language AI Research: A Deaf-Led Call to Reevaluate Research Agendascited by 19
  13. 2025Predicting 4D Hand Trajectory from Monocular Videoscited by 19
  14. 2023Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstructioncited by 18
  15. 2024Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representationscited by 18
  16. 2024RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimationcited by 18
  17. 2023Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognitioncited by 17
  18. 2023Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoningcited by 16
  19. 2023A Graph-Based Approach for Category-Agnostic Pose Estimationcited by 16
  20. 2024DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recoverycited by 16
  21. 2023Holistic Representation Learning for Multitask Trajectory Anomaly Detectioncited by 15
  22. 2023Understanding the Challenges and Opportunities of Pose-based Anomaly Detectioncited by 14
  23. 2024MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotationscited by 14
  24. 2023Markerless human pose estimation for biomedical applications: a surveycited by 13
  25. 2023Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrasescited by 13
  26. 2023Improved Trajectory Reconstruction for Markerless Pose Estimationcited by 12
  27. 20234DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacementscited by 12
  28. 2025Towards Online Multi-Modal Social Interaction Understandingcited by 12
  29. 2022Beyond Object Recognition: A New Benchmark towards Object Concept Learningcited by 11
  30. 2023GaitPT: Skeletons Are All You Need For Gait Recognitioncited by 11
  31. 2023InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognitioncited by 11
  32. 2024Deep learning for 3D human pose estimation and mesh recovery: A surveycited by 11
  33. 2024Privacy-Preserving Video Anomaly Detection: A Surveycited by 11
  34. 2023Markerless Motion Capture and Biomechanical Analysis Pipelinecited by 10
  35. 2024CapeX: Category-Agnostic Pose Estimation from Textual Point Explanationcited by 9
  36. 2025ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightnesscited by 9
  37. 2023AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesiscited by 8
  38. 2023Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Drivingcited by 8

50 most cited of 199 All 199 (JSON)