mlsanityData to 7 Oct 2026

Learning Delicate Local Representations for Multi-Person Pose Estimation

arXiv 2003.04030 ↗First posted 9 Mar 2020cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN/

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 17; 2022: 18; 2023: 11; 2024: 14; 2025: 5.

65 papers.

Sort:

By area:

  1. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  2. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  3. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  4. 2021Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstructioncited by 110
  5. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
  6. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  7. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  8. 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
  9. 2022HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imagingcited by 66
  10. 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
  11. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  12. 2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
38 more
  1. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  2. 2023Human Pose as Compositional Tokenscited by 45
  3. 2022Flow-Guided Sparse Transformer for Video Deblurringcited by 43
  4. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  5. 2021TFPose: Direct Human Pose Estimation with Transformerscited by 42
  6. 2021FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutionscited by 34
  7. 2022Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Trainingcited by 29
  8. 2024NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Resultscited by 26
  9. 2022RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmarkcited by 24
  10. 20222D Human Pose Estimation: A Surveycited by 21
  11. 2021The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimationcited by 18
  12. 2024RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimationcited by 18
  13. 2023Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Videocited by 17
  14. 2021InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimationcited by 13
  15. 2022Efficient Mirror Detection via Multi-level Heterogeneous Learningcited by 13
  16. 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10
  17. 2022ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wildcited by 9
  18. 2021Location-Sensitive Visual Recognition with Cross-IOU Losscited by 8
  19. 2024Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learningcited by 8
  20. 2023Lightweight Super-Resolution Head for Human Pose Estimationcited by 7
  21. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  22. 2023SniffyArt: The Dataset of Smelling Personscited by 6
  23. 2021SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimationcited by 5
  24. 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Modelscited by 5
  25. 2024PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptionscited by 4
  26. 2024Human Modelling and Pose Estimation Overviewcited by 4
  27. 2022DPIT: Dual-Pipeline Integrated Transformer for Human Pose Estimationcited by 3
  28. 2023Bias-Compensated Integral Regression for Human Pose Estimationcited by 3
  29. 2023PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detectioncited by 2
  30. 2024Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approachcited by 2
  31. 2024The Influence of Faulty Labels in Data Sets on Human Pose Estimationcited by 2
  32. 2024Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Losscited by 2
  33. 2021Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimationcited by 1
  34. 2021FasterPose: A Faster Simple Baseline for Human Pose Estimationcited by 1
  35. 2024Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recoverycited by 1
  36. 2024LanePtrNet: Revisiting Lane Detection as Point Voting and Grouping on Curvescited by 1
  37. 2024G3R: Generating Rich and Fine-grained mmWave Radar Data from 2D Videos for Generalized Gesture Recognitioncited by 1
  38. 2025VISUALCENT: Visual Human Analysis using Dynamic Centroid Representationcited by 1

50 most cited of 65 All 65 (JSON)