mlsanityData to 7 Oct 2026

Enhancing Egocentric 3D Pose Estimation with Third Person Views

arXiv 2201.02017 ↗First posted 6 Jan 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera. The key idea is to leverage high-level features linking first- and third-views in a joint embedding space. To learn such embedding space we introduce First2Third-Pose, a new paired synchronized dataset of nearly 2,000 videos depicting human activities captured from both first- and third-view perspectives. We explicitly consider spatial- and motion-domain features, combined using a semi-Siamese architecture trained in a self-supervised fashion. Experimental results demonstrate that the joint multi-view embedded space learned with our dataset is useful to extract discriminatory features from arbitrary single-view egocentric videos, without needing domain adaptation nor knowledge of camera parameters. We achieve significant improvement of egocentric 3D body pose estimation performance on two unconstrained datasets, over three supervised state-of-the-art approaches. Our dataset and code will be available for research purposes.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 6 Jan 2022.

Builds on

34 of 54 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  4. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  5. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  6. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  7. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  8. 2017Integral Human Pose Regressioncited by 255
  9. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  10. 2017Compositional Human Pose Regressioncited by 124
  11. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  12. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
22 more
  1. 2018Actor and Observer: Joint Modeling of First and Third-Person Videoscited by 102
  2. 2021Ego-Exo: Transferring Visual Representations from Third-person to First-person Videoscited by 98
  3. 2019Ego-Pose Estimation and Forecasting as Real-Time PD Controlcited by 87
  4. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  5. 2019You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactionscited by 82
  6. 2019xR-EgoPose: Egocentric 3D Human Pose from an HMD Cameracited by 78
  7. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  8. 2017Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Imagecited by 73
  9. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  10. 2020FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integrationcited by 72
  11. 2018Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Cameracited by 67
  12. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  13. 2021Estimating Egocentric 3D Human Pose in Global Spacecited by 56
  14. 2016Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Videocited by 45
  15. 2016Structured Prediction of 3D Human Pose with Deep Neural Networkscited by 43
  16. 2016Deep Kinematic Pose Regressioncited by 40
  17. 2015Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimationcited by 37
  18. 2021Egocentric Pose Estimation from Human Vision Spancited by 27
  19. 20213D Human Pose, Shape and Texture from Low-Resolution Images and Videoscited by 26
  20. 2017Deep Multitask Architecture for Integrated 2D and 3D Human Sensingcited by 21
  21. 2017Identifying First-person Camera Wearers in Third-person Videoscited by 18
  22. 2020Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 1.

5 papers.

  1. 2024A Survey on 3D Egocentric Human Pose Estimationcited by 8
  2. 2025Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Visioncited by 8
  3. 2024Egocentric and Exocentric Methods: A Short Surveycited by 6
  4. 2025Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Imagescited by 1
  5. 2026EgoExoMoCap: Distributed Ego-Exo Human Motion Capturecited by 0