mlsanityData to 7 Oct 2026

Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation

arXiv 2109.03622 ↗First posted 8 Sep 2021cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

This paper studies the problem of multi-person pose estimation in a bottom-up fashion. With a new and strong observation that the localization issue of the center-offset formulation can be remedied in a local-window search scheme in an ideal situation, we propose a multi-person pose estimation approach, dubbed as LOGO-CAP, by learning the LOcal-GlObal Contextual Adaptation for human Pose. Specifically, our approach learns the keypoint attraction maps (KAMs) from the local keypoints expansion maps (KEMs) in small local windows in the first step, which are subsequently treated as dynamic convolutional kernels on the keypoints-focused global heatmaps for contextual adaptation, achieving accurate multi-person pose estimation. Our method is end-to-end trainable with near real-time inference speed in a single forward pass, obtaining state-of-the-art performance on the COCO keypoint benchmark for bottom-up human pose estimation. With the COCO trained model, our method also outperforms prior arts by a large margin on the challenging OCHuman dataset.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 34 of its 44 references that are in the map. First posted on arXiv 8 Sep 2021.

Builds on

34 of 44 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2019Objects as Pointscited by 1,172
  10. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  11. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  12. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
22 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  2. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  3. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  4. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  5. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  6. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  7. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  8. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  9. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  10. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  11. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  12. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  13. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  14. 2021Pose Recognition with Cascade Transformerscited by 99
  15. 2019Single-Stage Multi-Person Pose Machinescited by 95
  16. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  17. 2020Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimationcited by 52
  18. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  19. 2019Mixture Dense Regression for Object Detection and Human Pose Estimationcited by 29
  20. 2019Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimationcited by 27
  21. 2019Attentive Normalizationcited by 13
  22. 2020Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimatescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 1; 2025: 2; 2026: 1.

14 papers.

Sort:

  1. 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
  2. 2023Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimationcited by 26
  3. 2023Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguitycited by 13
  4. 2023You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perceptioncited by 9
  5. 2023Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimationcited by 7
  6. 2024Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditionscited by 7
  7. 2023LAMP: Leveraging Language Prompts for Multi-person Pose Estimationcited by 4
  8. 2023Single-stage Multi-human Parsing via Point Sets and Center-based Offsetscited by 2
  9. 2023Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approachcited by 2
  10. 2023BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimationcited by 2
  11. 2023MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Modelcited by 1
  12. 2025VISUALCENT: Visual Human Analysis using Dynamic Centroid Representationcited by 1
2 more
  1. 2026UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimationcited by 1
  2. 2025Keypoints as Dynamic Centroids for Unified Human Pose and Segmentationcited by 0