AI Paper Atlas

Research map / 3D vision / Human pose estimation

View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

Ting Liu, Jennifer J. Sun, Long Zhao, Jiaping Zhao, Liangzhe Yuan, Yuxiao Wang, Liang-Chieh Chen, Florian Schroff, Hartwig Adam

IJCV 2021 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 22 citations (OpenAlex)

Read the paperCheck 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
add camera augmentation (random 3D rotations) (ablation)Pr-VIPE · 3DHP (all cameras) retrievalHit@1: 19.8 -> 27.3Improved
add camera augmentation (ablation)Pr-VIPE · H3.6M hold-out retrievalHit@1: 74.6 -> 72.9Hurt
use probabilistic embedding instead of L2-normalized point embedding (ablation)Pr-VIPE · H3.6M retrievalHit@1: 73.2 -> 74.6Improved
use Pr-VIPE instead of 3D lifting with Procrustes alignmentPr-VIPE · H3.6M retrievalHit@1: 68.8 -> 74.6Improved
raise Pr-VIPE embedding dimension from 16D to 32D (ablation)Pr-VIPE · H3.6M hold-out subsetHit@1: 78.3 -> 81.6Improved
add keypoint dropout (independent) during training (ablation)Pr-VIPE · H3.6M targeted occlusionHit@1: 2.52 -> 66.2Improved
add structured instead of independent keypoint dropout (ablation)Pr-VIPE · H3.6M real-distribution occlusionHit@1: 70.3 -> 71.0Improved
add keypoint dropout to training (ablation)Pr-VIPE · H3.6M no occlusionHit@1: 72.9 -> 71.7Hurt
use independent keypoint dropout instead of none (ablation)Pr-VIPE · 3DPW realistic occlusionHit@1: 43.8 -> 64.6Improved
use temporal Pr-VIPE instead of stacked frame embeddings (ablation)Pr-VIPE · Penn Action video alignmentKendall's Tau: 0.7405 -> 0.7810Improved
use groundtruth 2D keypoints instead of detected (ablation)Pr-VIPE · H3.6M retrievalHit@1: 74.6 -> 97.2Improved
increase number of samples K from 10 to 20 (ablation)Pr-VIPE · H3.6M retrievalHit@1: 72.6 -> 72.9No clear effect

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