AI Paper Atlas

Research map / 3D vision / Human pose estimation

Context Modeling in 3D Human Pose Estimation: A Unified Perspective

CVPR 2021 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 84 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 ContextPose to the pose estimator3D pose estimator · Human3.6M S9MPJPE (mm): 54.38 -> 50.24Helped
Add ContextPose to the pose estimator3D pose estimator · Human3.6M S11MPJPE (mm): 35.12 -> 34.10Helped
Add ContextPoseBaseline pose estimator trained on Human3.6M · MPI-INF-3DHP, ALLPCK: 71.3% -> 80.5%Helped
Add pairwise attention (ablation)ContextPose · Human3.6M S9MPJPE (mm): 52.00 -> 50.24Helped
Add pairwise attention (ablation)ContextPose · Human3.6M S9MPLLE (mm): 14.58 -> 14.13Helped
Add global attention (ablation)ContextPose · Human3.6M S9MPJPE (mm): 52.46 -> 50.24Helped
Add global attention (ablation)ContextPose · Human3.6M S11MPJPE (mm): 34.98 -> 34.10No clear effect
Combine pairwise attention and global attention (ablation)ContextPose · Human3.6M S9MPJPE (mm): 54.38 -> 50.24Helped
Use ContextPose with limb-length priors3D pose estimator trained on Human3.6M · MPI-INF-3DHP, ALLAUC: 35.0 -> 42.7Helped

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