mlsanityData to 14 Oct 2026

Refinement Module based on Parse Graph for Human Pose Estimation

arXiv 2501.11069 ↗First posted 19 Jan 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Parse graphs have been widely used in Human Pose Estimation (HPE) to model the hierarchical structure and context relations of the human body. However, such methods often suffer from parameter redundancy. More importantly, they rely on predefined network structures, which limits their use in other methods. To address these issues, we propose a new context relation and hierarchical structure modeling module, RMPG (Refinement Module based on Parse Graph). RMPG adaptively refines feature maps through recursive top-down decomposition of feature maps and bottom-up composition of sub-node feature maps with context information. Through recursive hierarchical composition, RMPG fuses local details and global semantics into more structured feature representations, accompanied by context information, thereby improving the accuracy of joint inference. RMPG can be flexibly embedded as a plug-in into various mainstream HPE networks. Moreover, by supervising sub-node features map, RMPG learns the context relations and hierarchical structure between different body parts with fewer parameters. Extensive experiments show that RMPG improves performance across different architectures while effectively modeling hierarchical and context relations of the human body with fewer parameters. The RMPG code can be found at https://github.com/lushbng/RMPG.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 65 references that are in the map. First posted on arXiv 19 Jan 2025.

Builds on

37 of 65 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2018YOLOv3: An Incremental Improvementcited by 2,659
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  7. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  8. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  9. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  10. 2016Convolutional Pose Machinescited by 325
  11. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  12. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 107
25 more
  1. 2022Deep Hierarchical Semantic Segmentationcited by 84
  2. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  3. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  4. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  5. 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
  6. 2017Human Pose Regression by Combining Indirect Part Detection and Contextual Informationcited by 52
  7. 2023Human Pose as Compositional Tokenscited by 45
  8. 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37
  9. 2017Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimationcited by 35
  10. 2020Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinementcited by 33
  11. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  12. 2019Human Pose Estimation with Spatial Contextual Informationcited by 21
  13. 2017Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimationcited by 18
  14. 2023Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attentioncited by 12
  15. 2023SHaRPose: Sparse High-Resolution Representation for Human Pose Estimationcited by 11
  16. 2021Low-resolution Human Pose Estimationcited by 10
  17. 2016CRF-CNN: Modeling Structured Information in Human Pose Estimationcited by 9
  18. 2017Self Adversarial Training for Human Pose Estimationcited by 8
  19. 2021An Adversarial Human Pose Estimation Network Injected with Graph Structurecited by 8
  20. 2017An Implementation of Faster RCNN with Study for Region Samplingcited by 7
  21. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  22. 2023Learning Structure-Guided Diffusion Model for 2D Human Pose Estimationcited by 5
  23. 2017Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localizationcited by 3
  24. 2024Occluded Human Pose Estimation based on Limb Joint Augmentationcited by 3
  25. 2015Image Segmentation Using Hierarchical Merge Treecited by 1

Built on by

Not cited yet.