AI Paper Atlas

Research map / 3D vision / Human pose estimation

Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition

Diogo Carbonera Luvizon, David Picard, Hedi Tabia

TPAMI 2020 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 161 citations (OpenAlex)

Read the paper

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 action recognition (multi-task training) to pose estimation (ablation)Multi-task network · Human3.6MMPJPE (mm): 49.5 -> 48.6Improved
add pose supervision to action-only training (ablation)Multi-task network · Penn Actionaccuracy (%): 87.5 -> 97.4Improved
add MPII data for pose supervision (ablation)Multi-task network · Penn Actionaccuracy (%): 97.4 -> 98.2Improved
add multi-task training (pose supervision) (ablation)Multi-task network · NTU RGB+D (cross-subject)accuracy (%): 88.0 -> 89.9Improved
supervise all prediction blocks instead of only the last (ablation)Multi-PB network (10M) · MPII valPCKh (%): 84.2 -> 85.1Improved
supervise all prediction blocks instead of only the last (ablation)Multi-PB network (10M) · Penn Actionaccuracy (%): 97.5 -> 98.1Improved
scale to full Multi-PB network (P=8, L=4, 26M) (ablation)Multi-PB network · MPII valPCKh (%): 85.1 -> 88.3Improved
add appearance features to pose features (ablation)Action recognition part · Penn Actionaccuracy (%): 97.4 -> 98.1Improved
add pose features to appearance features (ablation)Action recognition part · Penn Actionaccuracy (%): 97.9 -> 98.1Improved
add decoupled action poses (ablation)Combined features · Penn Actionaccuracy (%): 98.1 -> 98.2Improved
add decoupled action poses (ablation)Combined features · MPII valPCKh (%): 85.1 -> 85.4Improved
add joint confidence scores to weight poses (ablation)Pose features · Penn Actionaccuracy (%)No 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