mlsanityData to 7 Oct 2026

Deep High-Resolution Representation Learning for Human Pose Estimation

arXiv 1902.09212 ↗First posted 25 Feb 2019cs.CVcited by 1,339

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. The code and models have been publicly available at urlhttps://github.com/leoxiaobin/deep-high-resolution-net.pytorch.

Key facts. Cited by 1,339 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 260; 2022: 271; 2023: 281; 2024: 242; 2025: 186; 2026: 99.

1,339 papers.

Sort:

By area:

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2021Grounded Language-Image Pre-trainingcited by 1,147
  3. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  4. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  5. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  6. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  7. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  8. 2021Conditional DETR for Fast Training Convergencecited by 422
  9. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  10. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  11. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 320
  12. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 317
38 more
  1. 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 307
  2. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
  3. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  4. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  5. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  6. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  7. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  8. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  9. 2022Transformers in Medical Imaging: A Surveycited by 245
  10. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  11. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  12. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  13. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  14. 2022Thin-Plate Spline Motion Model for Image Animationcited by 209
  15. 2021Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encodingcited by 207
  16. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  17. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  18. 2022Focal Modulation Networkscited by 186
  19. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  20. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  21. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  22. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  23. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  24. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  25. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  26. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  27. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  28. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  29. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 122
  30. 2023DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Modelscited by 122
  31. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  32. 2021A Survey of Visual Transformerscited by 117
  33. 2022Revealing the Dark Secrets of Masked Image Modelingcited by 117
  34. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
  35. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  36. 2021GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognitioncited by 114
  37. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  38. 2022MobileOne: An Improved One millisecond Mobile Backbonecited by 109

50 most cited of 1,339 All 1,339 (JSON)