mlsanityData to 7 Oct 2026

Human Pose as Compositional Tokens

arXiv 2303.11638 ↗First posted 21 Mar 2023cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Human pose is typically represented by a coordinate vector of body joints or their heatmap embeddings. While easy for data processing, unrealistic pose estimates are admitted due to the lack of dependency modeling between the body joints. In this paper, we present a structured representation, named Pose as Compositional Tokens (PCT), to explore the joint dependency. It represents a pose by M discrete tokens with each characterizing a sub-structure with several interdependent joints. The compositional design enables it to achieve a small reconstruction error at a low cost. Then we cast pose estimation as a classification task. In particular, we learn a classifier to predict the categories of the M tokens from an image. A pre-learned decoder network is used to recover the pose from the tokens without further post-processing. We show that it achieves better or comparable pose estimation results as the existing methods in general scenarios, yet continues to work well when occlusion occurs, which is ubiquitous in practice. The code and models are publicly available at https://github.com/Gengzigang/PCT.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 89 of its 116 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

89 of 116 references.

References · 89

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2017Mask R-CNNcited by 7,259
  8. 2017Neural Discrete Representation Learningcited by 4,650
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
38 more
  1. 2019Objects as Pointscited by 1,172
  2. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  3. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  4. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  5. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  6. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  7. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 420
  8. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  9. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  10. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  11. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  12. 2016Convolutional Pose Machinescited by 325
  13. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  14. 2017Integral Human Pose Regressioncited by 255
  15. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  16. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  17. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  18. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  19. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  20. 2022A Unified Sequence Interface for Vision Taskscited by 152
  21. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  22. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  23. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  24. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
  25. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  26. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  27. 2020TransPose: Keypoint Localization via Transformercited by 126
  28. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  29. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  30. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  31. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
  32. 2021Pose Recognition with Cascade Transformerscited by 99
  33. 2019Single-Stage Multi-Person Pose Machinescited by 95
  34. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  35. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  36. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  37. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  38. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 21; 2025: 14; 2026: 5.

45 papers.

Sort:

By area:

  1. 2023InstructDiffusion: A Generalist Modeling Interface for Vision Taskscited by 162
  2. 2024TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representationcited by 93
  3. 2024ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuningcited by 68
  4. 2023MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representationscited by 58
  5. 2024MoGenTS: Motion Generation based on Spatial-Temporal Joint Modelingcited by 40
  6. 2023X-Pose: Detecting Any Keypointscited by 21
  7. 2024ExpertAF: Expert Actionable Feedback from Videocited by 17
  8. 2024DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recoverycited by 16
  9. 2024MEGA: Masked Generative Autoencoder for Human Mesh Recoverycited by 13
  10. 2024Video-Based Human Pose Regression via Decoupled Space-Time Aggregationcited by 10
  11. 2023HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigationcited by 9
  12. 2025HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimationcited by 8
33 more
  1. 2024A Survey and Evaluation of Adversarial Attacks for Object Detectioncited by 7
  2. 2024Diversifying Human Pose in Synthetic Data for Aerial-view Human Detectioncited by 5
  3. 2024Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimationcited by 3
  4. 2024PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recoverycited by 2
  5. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
  6. 2024Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approachcited by 2
  7. 2025ExGes: Expressive Human Motion Retrieval and Modulation for Audio-Driven Gesture Synthesiscited by 2
  8. 2023Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuningcited by 1
  9. 2024GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolutioncited by 1
  10. 2024Waterfall Transformer for Multi-person Pose Estimationcited by 1
  11. 2024Measurement of Medial Elbow Joint Space using Landmark Detectioncited by 1
  12. 2025PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimationcited by 1
  13. 2025KB-DMGen: Knowledge-Based Global Guidance and Dynamic Pose Masking for Human Image Generationcited by 1
  14. 2025End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformercited by 1
  15. 2026WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimationcited by 1
  16. 2026Wave2Body: Rethinking mmWave Human Pose Estimation as Radar-to-Body Token Translationcited by 1
  17. 2024Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignmentcited by 0
  18. 2024Structure-Aware Human Body Reshaping with Adaptive Affinity-Graph Networkcited by 0
  19. 2024Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimationcited by 0
  20. 2024GateAttentionPose: Enhancing Pose Estimation with Agent Attention and Improved Gated Convolutionscited by 0
  21. 2024Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Imagescited by 0
  22. 2025Refinement Module based on Parse Graph for Human Pose Estimationcited by 0
  23. 2025Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generationcited by 0
  24. 2025Multi-view Video-Pose Pretraining for Operating Room Surgical Activity Recognitioncited by 0
  25. 2025Multi-Grained Feature Pruning for Video-Based Human Pose Estimationcited by 0
  26. 2025PromptGAR: Flexible Promptive Group Activity Recognitioncited by 0
  27. 2025Periodontal Bone Loss Analysis via Keypoint Detection With Heuristic Post-Processingcited by 0
  28. 2025Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimationcited by 0
  29. 2025PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modelingcited by 0
  30. 2025Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimationcited by 0
  31. 2026Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimationcited by 0
  32. 2026B'ezier Degradation Modeling for LiDAR-based Human Motion Capturecited by 0
  33. 2026Single-Query Person-Centric Bimanual Hand-Object Interaction Detectioncited by 0