mlsanityData to 7 Oct 2026

PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation

arXiv 2209.08194 ↗First posted 16 Sep 2022cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Recently, the vision transformer and its variants have played an increasingly important role in both monocular and multi-view human pose estimation. Considering image patches as tokens, transformers can model the global dependencies within the entire image or across images from other views. However, global attention is computationally expensive. As a consequence, it is difficult to scale up these transformer-based methods to high-resolution features and many views. In this paper, we propose the token-Pruned Pose Transformer (PPT) for 2D human pose estimation, which can locate a rough human mask and performs self-attention only within selected tokens. Furthermore, we extend our PPT to multi-view human pose estimation. Built upon PPT, we propose a new cross-view fusion strategy, called human area fusion, which considers all human foreground pixels as corresponding candidates. Experimental results on COCO and MPII demonstrate that our PPT can match the accuracy of previous pose transformer methods while reducing the computation. Moreover, experiments on Human 3.6M and Ski-Pose demonstrate that our Multi-view PPT can efficiently fuse cues from multiple views and achieve new state-of-the-art results.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 65 of its 78 references that are in the map. First posted on arXiv 16 Sep 2022.

Builds on

65 of 78 references.

References · 65

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2017Mask R-CNNcited by 7,259
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  11. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  12. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
38 more
  1. 2017Non-local Neural Networkscited by 2,290
  2. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  3. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  4. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  5. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 849
  8. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  9. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  10. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  11. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  12. 2019Q-BERT: Hessian Based Ultra Low Precision Quantization of BERTcited by 355
  13. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  14. 2016Convolutional Pose Machinescited by 325
  15. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  16. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  17. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  18. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  19. 2021Chasing Sparsity in Vision Transformers: An End-to-End Explorationcited by 181
  20. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  21. 2019Learnable Triangulation of Human Posecited by 160
  22. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  23. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  24. 2020TransPose: Keypoint Localization via Transformercited by 126
  25. 2020Epipolar Transformerscited by 117
  26. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
  27. 2021Pose Recognition with Cascade Transformerscited by 99
  28. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  29. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  30. 2022Unified Visual Transformer Compressioncited by 79
  31. 2017Multi-Context Attention for Human Pose Estimationcited by 66
  32. 2022DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformerscited by 65
  33. 2021AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentationcited by 48
  34. 2016Deep Learning on Lie Groups for Skeleton-based Action Recognitioncited by 42
  35. 2018Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPosecited by 42
  36. 2021TFPose: Direct Human Pose Estimation with Transformerscited by 42
  37. 2020AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wildcited by 40
  38. 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 9; 2024: 7; 2025: 6; 2026: 2.

27 papers.

Sort:

By area:

  1. 2025Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodalitycited by 49
  2. 2022TORE: Token Reduction for Efficient Human Mesh Recovery with Transformercited by 41
  3. 2023Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modelingcited by 41
  4. 2022Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Trainingcited by 24
  5. 2023CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformercited by 24
  6. 2023TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecastingcited by 22
  7. 2023Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimationcited by 15
  8. 2022Identity-Aware Hand Mesh Estimation and Personalization from RGB Imagescited by 11
  9. 2024Learning Multi-view Anomaly Detection with Efficient Adaptive Selectioncited by 9
  10. 2023All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletescited by 8
  11. 2023HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learningcited by 7
  12. 2025Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identificationcited by 7
15 more
  1. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  2. 2025H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformerscited by 5
  3. 2024Occluded Human Pose Estimation based on Limb Joint Augmentationcited by 3
  4. 2025Multi-View Industrial Anomaly Detection with Epipolar Constrained Cross-View Fusioncited by 3
  5. 2023Geometry-Biased Transformer for Robust Multi-View 3D Human Pose Reconstructioncited by 2
  6. 2024DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimationcited by 2
  7. 2024PO-GUISE+: Pose and object guided transformer token selection for efficient driver action recognitioncited by 2
  8. 2025RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Liftingcited by 2
  9. 2024MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detectioncited by 1
  10. 2026Unconstrained Multi-view Human Pose Estimation with Algebraic Priorscited by 1
  11. 2023Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimationcited by 0
  12. 2023RSB-Pose: Robust Short-Baseline Binocular 3D Human Pose Estimation with Occlusion Handlingcited by 0
  13. 2024Self-learning Canonical Space for Multi-view 3D Human Pose Estimationcited by 0
  14. 2025C-DOG: Multi-View Multi-instance Feature Association Using Connected δ-Overlap Graphscited by 0
  15. 2026HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusioncited by 0