mlsanityData to 14 Oct 2026

Global Relation Modeling and Refinement for Bottom-Up Human Pose Estimation

arXiv 2303.14888 ↗First posted 27 Mar 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we concern on the bottom-up paradigm in multi-person pose estimation (MPPE). Most previous bottom-up methods try to consider the relation of instances to identify different body parts during the post processing, while ignoring to model the relation among instances or environment in the feature learning process. In addition, most existing works adopt the operations of upsampling and downsampling. During the sampling process, there will be a problem of misalignment with the source features, resulting in deviations in the keypoint features learned by the model. To overcome the above limitations, we propose a convolutional neural network for bottom-up human pose estimation. It invovles two basic modules: (i) Global Relation Modeling (GRM) module globally learns relation (e.g., environment context, instance interactive information) among region of image by fusing multiple stages features in the feature learning process. It combines with the spatial-channel attention mechanism, which focuses on achieving adaptability in spatial and channel dimensions. (ii) Multi-branch Feature Align (MFA) module aggregates features from multiple branches to align fused feature and obtain refined local keypoint representation. Our model has the ability to focus on different granularity from local to global regions, which significantly boosts the performance of the multi-person pose estimation. Our results on the COCO and CrowdPose datasets demonstrate that it is an efficient framework for multi-person pose estimation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

33 of 43 references.

References · 33

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2017Squeeze-and-Excitation Networkscited by 4,789
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  7. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  8. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  9. 2016Convolutional Pose Machinescited by 325
  10. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  11. 2017Integral Human Pose Regressioncited by 256
  12. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
21 more
  1. 2014Efficient Object Localization Using Convolutional Networkscited by 227
  2. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  3. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 212
  4. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  5. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  6. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  7. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  8. 2019Single-Stage Multi-Person Pose Machinescited by 95
  9. 2017Multi-Context Attention for Human Pose Estimationcited by 66
  10. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  11. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  12. 2020Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimationcited by 52
  13. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  14. 2015Object detection via a multi-region & semantic segmentation-aware CNN modelcited by 47
  15. 2019Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Informationcited by 35
  16. 2019Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimationcited by 27
  17. 20183D Human Pose Estimation with 2D Marginal Heatmapscited by 20
  18. 2022Lite Pose: Efficient Architecture Design for 2D Human Pose Estimationcited by 16
  19. 2016Chained Predictions Using Convolutional Neural Networkscited by 15
  20. 2015Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimationcited by 14
  21. 2020Structured Context Enhancement Network for Mouse Pose Estimationcited by 3

Built on by

Not cited yet.