mlsanityData to 7 Oct 2026

Towards Accurate Cross-Domain In-Bed Human Pose Estimation

arXiv 2110.03578 ↗First posted 7 Oct 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Human behavioral monitoring during sleep is essential for various medical applications. Majority of the contactless human pose estimation algorithms are based on RGB modality, causing ineffectiveness in in-bed pose estimation due to occlusions by blankets and varying illumination conditions. Long-wavelength infrared (LWIR) modality based pose estimation algorithms overcome the aforementioned challenges; however, ground truth pose generations by a human annotator under such conditions are not feasible. A feasible solution to address this issue is to transfer the knowledge learned from images with pose labels and no occlusions, and adapt it towards real world conditions (occlusions due to blankets). In this paper, we propose a novel learning strategy comprises of two-fold data augmentation to reduce the cross-domain discrepancy and knowledge distillation to learn the distribution of unlabeled images in real world conditions. Our experiments and analysis show the effectiveness of our approach over multiple standard human pose estimation baselines.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 7 Oct 2021.

Builds on

15 of 21 references.

References · 15

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  4. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  5. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  6. 2016Convolutional Pose Machinescited by 325
  7. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 205
  8. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  9. 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
  10. 2020Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillationcited by 46
  11. 2021Regressive Domain Adaptation for Unsupervised Keypoint Detectioncited by 34
  12. 2020Generative Pseudo-label Refinement for Unsupervised Domain Adaptationcited by 24
3 more
  1. 2019Seeing Under the Cover: A Physics Guided Learning Approach for In-Bed Pose Estimationcited by 17
  2. 2020Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptationcited by 12
  3. 2020Simultaneously-Collected Multimodal Lying Pose Dataset: Towards In-Bed Human Pose Monitoring under Adverse Vision Conditionscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 0; 2024: 1; 2025: 1; 2026: 1.

6 papers.

  1. 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimationcited by 9
  2. 2022Under the Cover Infant Pose Estimation using Multimodal Datacited by 6
  3. 2022Towards Simple and Accurate Human Pose Estimation with Stair Networkcited by 0
  4. 2024In-Bed Pose Estimation: A Reviewcited by 0
  5. 2025Improving the Plausibility of Pressure Distributions Synthesized from Depth Image through Generative Modelingcited by 0
  6. 2026Geometry-Conditioned Diffusion for Occlusion-Robust In-Bed Pose Estimationcited by 0