AI Paper Atlas

Research map / 3D vision / Human pose estimation

Estimating Egocentric 3D Human Pose in the Wild With External Weak Supervision

Jian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar, Diogo Luvizon, Christian Theobalt

CVPR 2022 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 38 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
combine egocentric and external-view constraints in spatio-temporal pseudo-label optimization3D pose pseudo-label generation · Wang et al. datasetPA-MPJPE: 57.19 vs 68.13Improved
train on EgoPW pseudo-labels and use the proposed external-view feature supervision and domain adaptationsingle-frame egocentric pose estimation · Wang et al.’s test datasetPA-MPJPE: 81.71 vs 89.67Improved
train on EgoPW pseudo-labels and use the proposed external-view feature supervision and domain adaptationsingle-frame egocentric pose estimation · Mo2Cap2 test datasetPA-MPJPE: 83.17 vs 86.85Improved
add external-view supervision for pseudo-label generation (ablation)egocentric pose estimation network · Wang et al.’s test datasetPA-MPJPE: 90.05 -> 81.71Improved
add adversarial external-feature representation learning (ablation)egocentric pose estimation network · Wang et al.’s test datasetPA-MPJPE: 85.46 -> 81.71Improved
add adversarial domain adaptation between synthetic and real images (ablation)egocentric pose estimation network · Wang et al.’s test datasetPA-MPJPE: 84.22 -> 81.71Improved
use the full method rather than unsupervised domain adaptation alone (ablation)egocentric pose estimation network · Wang et al.’s test datasetPA-MPJPE: 91.56 -> 81.71Improved
add external-view supervision for pseudo-label generation (ablation)egocentric pose estimation network · Wang et al.’s test datasetBA-MPJPE: 68.99 -> 64.87Improved
add adversarial external-feature representation learning (ablation)egocentric pose estimation network · Wang et al.’s test datasetBA-MPJPE: 67.01 -> 64.87Improved
add adversarial domain adaptation between synthetic and real images (ablation)egocentric pose estimation network · Wang et al.’s test datasetBA-MPJPE: 66.48 -> 64.87Improved
use the full method rather than unsupervised domain adaptation alone (ablation)egocentric pose estimation network · Wang et al.’s test datasetBA-MPJPE: 69.17 -> 64.87Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy