atlas

Research map / 3D vision / Human pose estimation

Structured Feature Learning for Pose Estimation

CVPR 2016 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 288 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 single upward-direction feature-level message passing (ablation)VGG-16 pose baseline · FLIC testmean strict PCP: 75.1 -> 87.9Helped
Add bidirectional tree message passing instead of single-direction passing (ablation)Structured Feature Learning · FLIC testmean strict PCP: 87.9 -> 93.4Helped
Add multiple appearance-mixture score maps per joint (ablation)Bi-direct · FLIC testmean strict PCP: 93.4 -> 95.2Helped
Add structured feature learning with bidirectional message passing and multiple score maps (ablation)VGG-16 pose baseline · FLIC testmean strict PCP: 75.1 -> 95.2Helped
Use structured feature learning instead of the strongest reported baselinePose estimation · FLIC testmean strict PCP: 91.9 -> 95.2Helped
Use structured feature learning instead of the strongest reported baselinePose estimation · LSP testmean strict PCP: 75.0 -> 80.8Helped

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