mlsanityData to 7 Oct 2026

Stacked Hourglass Networks for Human Pose Estimation

arXiv 1603.06937 ↗First posted 22 Mar 2016cs.CVcited by 913

Not on the map. Why?

Abstract (arXiv)

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

Key facts. Cited by 913 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 333; 2022: 228; 2023: 162; 2024: 100; 2025: 57; 2026: 33.

913 papers.

Sort:

By area:

  1. 2021Multi-Stage Progressive Image Restorationcited by 813
  2. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  3. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  4. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  5. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  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. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  9. 2023Sequential Modeling Enables Scalable Learning for Large Vision Modelscited by 212
  10. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  11. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  12. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
38 more
  1. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  2. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  3. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  4. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  5. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  6. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  7. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  8. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  9. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  10. 2021Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networkscited by 141
  11. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 140
  12. 2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
  13. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  14. 2021Probabilistic two-stage detectioncited by 130
  15. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  16. 2021AP-10K: A Benchmark for Animal Pose Estimation in the Wildcited by 123
  17. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  18. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
  19. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
  20. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  21. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  22. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 106
  23. 2022Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generationcited by 106
  24. 2021Oriented RepPoints for Aerial Object Detectioncited by 102
  25. 2021Pose Recognition with Cascade Transformerscited by 99
  26. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
  27. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  28. 2022Towards End-to-End Unified Scene Text Detection and Layout Analysiscited by 96
  29. 2021Reformulating HOI Detection as Adaptive Set Predictioncited by 95
  30. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 95
  31. 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 95
  32. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  33. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  34. 2022HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentationcited by 94
  35. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  36. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  37. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  38. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91

50 most cited of 913 All 913 (JSON)