mlsanityData to 7 Oct 2026

Improved TokenPose with Sparsity

arXiv 2311.09653 ↗First posted 16 Nov 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Over the past few years, the vision transformer and its various forms have gained significance in human pose estimation. By treating image patches as tokens, transformers can capture global relationships wisely, estimate the keypoint tokens by leveraging the visual tokens, and recognize the posture of the human body. Nevertheless, global attention is computationally demanding, which poses a challenge for scaling up transformer-based methods to high-resolution features. In this paper, we introduce sparsity in both keypoint token attention and visual token attention to improve human pose estimation. Experimental results on the MPII dataset demonstrate that our model has a higher level of accuracy and proved the feasibility of the method, achieving new state-of-the-art results. The idea can also provide references for other transformer-based models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 45 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

40 of 45 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  10. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
28 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  2. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 849
  3. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  4. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  5. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  6. 2019Attention Augmented Convolutional Networkscited by 363
  7. 2019Q-BERT: Hessian Based Ultra Low Precision Quantization of BERTcited by 355
  8. 2016Convolutional Pose Machinescited by 325
  9. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  10. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  11. 2021Chasing Sparsity in Vision Transformers: An End-to-End Explorationcited by 181
  12. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  13. 2021Transformer for Single Image Super-Resolutioncited by 150
  14. 2020Disentangled Non-Local Neural Networkscited by 132
  15. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  16. 2020TransPose: Keypoint Localization via Transformercited by 126
  17. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
  18. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  19. 2022Unified Visual Transformer Compressioncited by 79
  20. 2022DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformerscited by 65
  21. 2021AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentationcited by 48
  22. 2018Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPosecited by 42
  23. 2020Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimationcited by 36
  24. 2022The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancycited by 35
  25. 2022VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformercited by 27
  26. 2022Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Trainingcited by 24
  27. 2020EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimationcited by 12
  28. 2022The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimationcited by 8

Built on by

Not cited yet.