mlsanityData to 7 Oct 2026

Rethinking on Multi-Stage Networks for Human Pose Estimation

arXiv 1901.00148 ↗First posted 1 Jan 2019cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-art on both MS COCO and MPII Human Pose dataset, justifying the effectiveness of a multi-stage architecture. The source code is publicly available for further research.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 13; 2022: 15; 2023: 17; 2024: 9; 2025: 4.

58 papers.

Sort:

By area:

  1. 2021Multi-Stage Progressive Image Restorationcited by 813
  2. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  3. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  4. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  5. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  6. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  7. 2023Human Pose as Compositional Tokenscited by 45
  8. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  9. 2021TFPose: Direct Human Pose Estimation with Transformerscited by 42
  10. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  11. 2021Regressive Domain Adaptation for Unsupervised Keypoint Detectioncited by 34
  12. 2021Supervision by Registration and Triangulation for Landmark Detectioncited by 30
38 more
  1. 2023MEGANE: Morphable Eyeglass and Avatar Networkcited by 24
  2. 2023RelightableHands: Efficient Neural Relighting of Articulated Hand Modelscited by 21
  3. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  4. 2024URHand: Universal Relightable Handscited by 17
  5. 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10
  6. 2023Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Modulecited by 10
  7. 2023Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfoldingcited by 10
  8. 2022Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimationcited by 9
  9. 2022ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wildcited by 9
  10. 2022Heatmap Distribution Matching for Human Pose Estimationcited by 9
  11. 2023Mitigating Motion Blur for Robust 3D Baseball Player Pose Modeling for Pitch Analysiscited by 8
  12. 2023Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimationcited by 7
  13. 2023Lightweight Super-Resolution Head for Human Pose Estimationcited by 7
  14. 2021OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimationcited by 6
  15. 2022NIMBLE: A Non-rigid Hand Model with Bones and Musclescited by 6
  16. 2024Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Camerascited by 6
  17. 2021SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimationcited by 5
  18. 2022Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimationcited by 4
  19. 2024PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptionscited by 4
  20. 2024Human Modelling and Pose Estimation Overviewcited by 4
  21. 2021BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representationscited by 3
  22. 2022DPIT: Dual-Pipeline Integrated Transformer for Human Pose Estimationcited by 3
  23. 2023Bias-Compensated Integral Regression for Human Pose Estimationcited by 3
  24. 2023A Mountain-Shaped Single-Stage Network for Accurate Image Restorationcited by 3
  25. 2022Multiview Detection with Cardboard Human Modelingcited by 2
  26. 2023Multi-View Person Matching and 3D Pose Estimation with Arbitrary Uncalibrated Camera Networkscited by 2
  27. 2021Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimationcited by 1
  28. 2023GoalieNet: A Multi-Stage Network for Joint Goalie, Equipment, and Net Pose Estimation in Ice Hockeycited by 1
  29. 2024Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformerscited by 1
  30. 2024Waterfall Transformer for Multi-person Pose Estimationcited by 1
  31. 2025RT-DEMT: A hybrid real-time acupoint detection model combining mamba and transformercited by 1
  32. 2025VISUALCENT: Visual Human Analysis using Dynamic Centroid Representationcited by 1
  33. 2021Adaptive Dilated Convolution For Human Pose Estimationcited by 0
  34. 2021Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimationcited by 0
  35. 2022Towards Simple and Accurate Human Pose Estimation with Stair Networkcited by 0
  36. 2022Lightweight Human Pose Estimation Using Heatmap-Weighting Losscited by 0
  37. 2022Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimationcited by 0
  38. 2023Unposed: Unsupervised Pose Estimation based Product Image Recommendationscited by 0

50 most cited of 58 All 58 (JSON)