AI Paper Atlas

Research map / 3D vision / Human pose estimation

Occlusion-Aware Networks for 3D Human Pose Estimation in Video

Yu Cheng, Bo Yang, Bo Wang, Wending Yan, Robby T. Tan

ICCV 2019 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 232 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 2D TCN (ablation)3D TCN baseline · Human3.6M Protocol #1MPJPE (mm): 54.0 -> 51.7Improved
add occlusion awareness (ablation)3D TCN + 2D TCN · Human3.6M Protocol #1MPJPE (mm): 51.7 -> 46.3Improved
add occlusion awareness (ablation)3D TCN + 2D TCN · Human3.6M Protocol #2P-MPJPE (mm): 40.5 -> 35.4Improved
add symmetry constraint (ablation)occlusion-aware TCNs · Human3.6M Protocol #1MPJPE (mm): 46.3 -> 45.8Improved
add adversarial learning (ablation)occlusion-aware TCNs · Human3.6M Protocol #1MPJPE (mm): 45.8 -> 45.1Improved
add pose regularization (ablation)occlusion-aware TCNs · Human3.6M Protocol #1MPJPE (mm): 45.1 -> 44.8Improved
add virtual view-angle data augmentation (ablation)occlusion-aware TCNs · Human3.6M Protocol #1MPJPE (mm): 44.8 -> 42.9Improved
increase sequence length from 16 to 128 (ablation)TCNs · Human3.6M Protocol #1MPJPE (mm): 55.4 -> 42.9Improved
increase sequence length from 128 to 256 (ablation)TCNs · Human3.6M Protocol #1MPJPE (mm): 42.9 -> 44.1Hurt
raise reliability threshold from 0.30 to 0.40 (ablation)TCNs · Human3.6M Protocol #1MPJPE (mm): 42.9 -> 44.2Hurt
lower reliability threshold from 0.30 to 0.20 (ablation)TCNs · Human3.6M Protocol #1MPJPE (mm): 42.9 -> 45.7Hurt
use occlusion-aware framework instead of Pavllo et al.3D pose estimation · Human3.6M Protocol #1MPJPE (mm): 46.8 -> 42.9Improved

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