mlsanityData to 7 Oct 2026

Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting

arXiv 2402.18330 ↗First posted 28 Feb 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

We present EgoTAP, a heatmap-to-3D pose lifting method for highly accurate stereo egocentric 3D pose estimation. Severe self-occlusion and out-of-view limbs in egocentric camera views make accurate pose estimation a challenging problem. To address the challenge, prior methods employ joint heatmaps-probabilistic 2D representations of the body pose, but heatmap-to-3D pose conversion still remains an inaccurate process. We propose a novel heatmap-to-3D lifting method composed of the Grid ViT Encoder and the Propagation Network. The Grid ViT Encoder summarizes joint heatmaps into effective feature embedding using self-attention. Then, the Propagation Network estimates the 3D pose by utilizing skeletal information to better estimate the position of obscure joints. Our method significantly outperforms the previous state-of-the-art qualitatively and quantitatively demonstrated by a 23.9% reduction of error in an MPJPE metric. Our source code is available in GitHub.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 28 Feb 2024.

Builds on

23 of 34 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  7. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  8. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  9. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  10. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  11. 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
  12. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
11 more
  1. 2019You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactionscited by 82
  2. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 81
  3. 2019xR-EgoPose: Egocentric 3D Human Pose from an HMD Cameracited by 78
  4. 2018Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Cameracited by 67
  5. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  6. 2021Estimating Egocentric 3D Human Pose in Global Spacecited by 56
  7. 2022UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capturecited by 56
  8. 2017Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gatescited by 54
  9. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 46
  10. 2022Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervisioncited by 33
  11. 2023Ego3DPose: Capturing 3D Cues from Binocular Egocentric Viewscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 6.

13 papers.

Sort:

By area:

  1. 2025Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understandingcited by 25
  2. 2025Challenges and Trends in Egocentric Vision: A Surveycited by 20
  3. 2025REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioningcited by 14
  4. 2024A Survey on 3D Egocentric Human Pose Estimationcited by 8
  5. 2025Bring Your Rear Cameras for Egocentric 3D Human Pose Estimationcited by 7
  6. 2025EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Cameracited by 6
  7. 2025FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Videocited by 5
  8. 2026Egocentric Visibility-Aware Human Pose Estimationcited by 1
  9. 2026E-3DPSM: A State Machine for Event-Based Egocentric 3D Human Pose Estimationcited by 1
  10. 2026EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Realitycited by 0
  11. 2026AG-EgoPose: Spatially Anchored Residual Correction with Action Context for Monocular Egocentric 3D Pose Estimationcited by 0
  12. 2026TSR-Ego: Temporally Guided Stereo Refinement Framework for Egocentric 3D Human Pose Estimationcited by 0
1 more
  1. 2026Learning human joint torques from pixelscited by 0