mlsanityData to 7 Oct 2026

TokenPose: Learning Keypoint Tokens for Human Pose Estimation

arXiv 2104.03516 ↗First posted 8 Apr 2021cs.CVcited by 106

Not on the map. Why?

Abstract (arXiv)

Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints. In this paper, we propose a novel approach based on Token representation for human Pose estimation~(TokenPose). In detail, each keypoint is explicitly embedded as a token to simultaneously learn constraint relationships and appearance cues from images. Extensive experiments show that the small and large TokenPose models are on par with state-of-the-art CNN-based counterparts while being more lightweight. Specifically, our TokenPose-S and TokenPose-L achieve 72.5 AP and 75.8 AP on COCO validation dataset respectively, with significant reduction in parameters (downarrow80.6%; downarrow 56.8%) and GFLOPs (downarrow 75.3%; downarrow 24.7%). Code is publicly available.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). Builds on 38 of its 46 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

38 of 46 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  11. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  12. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
26 more
  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  2. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  3. 2020Pre-Trained Image Processing Transformercited by 891
  4. 2021Transformer in Transformercited by 632
  5. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  6. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  7. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  8. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  9. 2016Convolutional Pose Machinescited by 325
  10. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  11. 2017Integral Human Pose Regressioncited by 255
  12. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  13. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  14. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  15. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  16. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  17. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  18. 2020Epipolar Transformerscited by 117
  19. 2018How to Start Training: The Effect of Initialization and Architecturecited by 109
  20. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  21. 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
  22. 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
  23. 2016Recurrent Human Pose Estimationcited by 27
  24. 201915 Keypoints Is All You Needcited by 23
  25. 2016Chained Predictions Using Convolutional Neural Networkscited by 15
  26. 2016Human Pose Estimation using Deep Consensus Votingcited by 14

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 27; 2023: 29; 2024: 24; 2025: 21.

106 papers.

Sort:

By area:

  1. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  2. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  3. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  4. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  5. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  6. 2022DETRs with Hybrid Matchingcited by 149
  7. 2021Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstructioncited by 110
  8. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
  9. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 94
  10. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  11. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  12. 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
38 more
  1. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  2. 2023UniHCP: A Unified Model for Human-Centric Perceptionscited by 59
  3. 2022Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learningcited by 47
  4. 2023Human Pose as Compositional Tokenscited by 45
  5. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  6. 2023HumanBench: Towards General Human-centric Perception with Projector Assisted Pretrainingcited by 38
  7. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  8. 2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimationcited by 36
  9. 2022Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformerscited by 33
  10. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  11. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  12. 2022RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmarkcited by 24
  13. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  14. 2023PoseRAC: Pose Saliency Transformer for Repetitive Action Countingcited by 17
  15. 2023Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Videocited by 17
  16. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  17. 2022AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimationcited by 13
  18. 2022QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Querycited by 13
  19. 2023Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguitycited by 13
  20. 2023DistilPose: Tokenized Pose Regression with Heatmap Distillationcited by 12
  21. 2024TCFormer: Visual Recognition via Token Clustering Transformercited by 12
  22. 2023Contextual Vision Transformers for Robust Representation Learningcited by 10
  23. 2022FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERcited by 9
  24. 2022Heatmap Distribution Matching for Human Pose Estimationcited by 9
  25. 2023GaitRef: Gait Recognition with Refined Sequential Skeletonscited by 9
  26. 2022Motion Transformer for Unsupervised Image Animationcited by 8
  27. 2023Capturing the motion of every joint: 3D human pose and shape estimation with independent tokenscited by 8
  28. 2023All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletescited by 8
  29. 2023APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyondcited by 8
  30. 2023FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentationcited by 7
  31. 2023Lightweight Super-Resolution Head for Human Pose Estimationcited by 7
  32. 2024Joint-Motion Mutual Learning for Pose Estimation in Videoscited by 7
  33. 2022FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimationcited by 6
  34. 2022AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regressioncited by 6
  35. 2022Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Maskscited by 6
  36. 2023Interaction-aware Joint Attention Estimation Using People Attributescited by 6
  37. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  38. 2024HumMUSS: Human Motion Understanding using State Space Modelscited by 6

50 most cited of 106 All 106 (JSON)