mlsanityData to 7 Oct 2026

Low-resolution Human Pose Estimation

arXiv 2109.09090 ↗First posted 19 Sep 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Human pose estimation has achieved significant progress on images with high imaging resolution. However, low-resolution imagery data bring nontrivial challenges which are still under-studied. To fill this gap, we start with investigating existing methods and reveal that the most dominant heatmap-based methods would suffer more severe model performance degradation from low-resolution, and offset learning is an effective strategy. Established on this observation, in this work we propose a novel Confidence-Aware Learning (CAL) method which further addresses two fundamental limitations of existing offset learning methods: inconsistent training and testing, decoupled heatmap and offset learning. Specifically, CAL selectively weighs the learning of heatmap and offset with respect to ground-truth and most confident prediction, whilst capturing the statistical importance of model output in mini-batch learning manner. Extensive experiments conducted on the COCO benchmark show that our method outperforms significantly the state-of-the-art methods for low-resolution human pose estimation.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 19 Sep 2021.

Builds on

33 of 44 references.

References · 33

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  8. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  10. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  11. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  12. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
21 more
  1. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  2. 2016Convolutional Pose Machinescited by 325
  3. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  4. 2017Integral Human Pose Regressioncited by 255
  5. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  6. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  7. 2019Generating 3D People in Scenes without Peoplecited by 127
  8. 2020Structure-Preserving Super Resolution with Gradient Guidancecited by 116
  9. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  10. 2018Numerical Coordinate Regression with Convolutional Neural Networkscited by 72
  11. 2017Pose-Normalized Image Generation for Person Re-identificationcited by 69
  12. 2017Multi-Context Attention for Human Pose Estimationcited by 66
  13. 2015P-CNN: Pose-based CNN Features for Action Recognitioncited by 58
  14. 2017Human Pose Regression by Combining Indirect Part Detection and Contextual Informationcited by 52
  15. 2020Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusioncited by 38
  16. 2020Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinementcited by 33
  17. 2019Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discriminationcited by 32
  18. 20203D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learningcited by 28
  19. 2021Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognitioncited by 24
  20. 2015Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimationcited by 14
  21. 2021An Adversarial Human Pose Estimation Network Injected with Graph Structurecited by 8

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 1; 2024: 2; 2025: 3.

10 papers.

  1. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
  2. 2022Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledgecited by 6
  3. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  4. 2022Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Personscited by 5
  5. 2021Single Person Pose Estimation: A Surveycited by 4
  6. 2024Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimationcited by 0
  7. 2024Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Imagescited by 0
  8. 2025Refinement Module based on Parse Graph for Human Pose Estimationcited by 0
  9. 2025Differentially Private 2D Human Pose Estimationcited by 0
  10. 2025Parse Graph-Based Visual-Language Interaction for Human Pose Estimationcited by 0