AI Paper Atlas

Research map / 3D vision / Human pose estimation

Not All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body Parts

Jue Wang, Shaoli Huang, Xinchao Wang, Dacheng Tao

ICCV 2019 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 70 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 progressive bi-directional dependency modeling among body parts (ablation)Baseline network · Human3.6M Protocol #1MPJPE (mm) average: 58.3 -> 56.9Improved
add predicted pose attributes as input (ablation)Progressive network · Human3.6M Protocol #1MPJPE (mm) average: 56.9 -> 52.6Improved
add pose attributes and progressive modeling (ablation)Baseline network · Human3.6M Protocol #1MPJPE (mm) wrist: 98.5 -> 87.6Improved
train attribute predictor on mixture of MPII and Human3.6M instead of Human3.6M only (ablation)attribute predictor · Human3.6M attribute accuracyaccuracy: 78.6 -> 82.7Improved
add domain adaptation to mixed training (ablation)attribute predictor · Human3.6M attribute accuracyaccuracy: 82.7 -> 84.0Improved
train on mixture with MPII instead of Human3.6M only (ablation)attribute predictor · MPI-INF-3DHP attribute accuracy (unseen)accuracy: 51.1 -> 67.7Improved
add domain adaptation to mixed training (ablation)attribute predictor · MPI-INF-3DHP attribute accuracy (unseen)accuracy: 67.7 -> 70.1Improved
use Ours instead of Dabral et al.3D pose estimator · Human3.6M Protocol #1MPJPE (mm) average: 55.5 -> 52.6Improved
use Ours instead of Pavlakos et al.3D pose estimator · Human3.6M Protocol #2MPJPE (mm) average: 41.8 -> 40.7Improved
use Ours instead of best prior method3D pose estimator · MPI-INF-3DHP3DPCK: 71.9 vs 71.9No clear effect
use Ours instead of best prior method3D pose estimator · MPI-INF-3DHPAUC: 35.3 -> 35.8Improved
use multi-task network instead of pretrained hourglass2D pose detection · MPII validationPCKh@0.5 average: 87.6 -> 88.5Improved

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