AI Paper Atlas

Research map / 3D vision / Human pose estimation

Recognizing Human Actions as the Evolution of Pose Estimation Maps

Mengyuan Liu, Junsong Yuan

CVPR 2018 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 356 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 heatmap evolution to 2D pose evolution (ablation)H1 on RGB video · NTU RGB+D cross subjectaccuracy: 72.96% -> 78.80%Improved
Add heatmap evolution to 2D pose evolution (ablation)H1 on RGB video · NTU RGB+D cross viewaccuracy: 77.21% -> 84.21%Improved
Add heatmap evolution to 2D pose evolution (ablation)H1 on RGB video · UTD-MHAD cross subjectaccuracy: 85.63% -> 92.51%Improved
Add heatmap evolution to 2D pose evolution (ablation)H1 on RGB video · PennAction half / halfaccuracy: 84.08% -> 91.39%Improved
Use spatial rank pooling instead of temporal rank pooling for heatmaps (ablation)Heatmap evolution (H3) · NTU RGB+D cross subjectaccuracy: 53.91% -> 72.75%Improved
Use spatial rank pooling instead of temporal rank pooling for heatmaps (ablation)Heatmap evolution (H3) · NTU RGB+D cross viewaccuracy: 54.10% -> 78.35%Improved
Use spatial rank pooling instead of temporal rank pooling for heatmaps (ablation)Heatmap evolution (H3) · UTD-MHAD cross subjectaccuracy: 58.88% -> 74.88%Improved
Use spatial rank pooling instead of temporal rank pooling for heatmaps (ablation)Heatmap evolution (H3) · PennAction half / halfaccuracy: 84.61% -> 87.02%Improved
Add depth coordinates to 2D pose evolution (ablation)Pose evolution from depth video · UTD-MHAD cross subjectaccuracy: 85.53% -> 89.44%Improved
Add depth coordinates to 2D pose evolution (ablation)Pose evolution from depth video · NTU RGB+D cross subjectaccuracy: 80.52% -> 82.38%Improved
Add depth coordinates to 2D pose evolution (ablation)Pose evolution from depth video · NTU RGB+D cross viewaccuracy: 85.75% -> 86.65%Improved
Add single-frame CNN features and annotated poses (ablation)H1 + H3 on PennAction · PennAction half / halfaccuracy: 91.39% -> 98.22%Improved

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