AI Paper Atlas

Research map / 3D vision / Human pose estimation

4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple Video Cameras

Yuxiang Zhang, Liang An, Tao Yu, Xiu Li, Kun Li, Yebin Liu

CVPR 2020 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 101 citations (OpenAlex)

Check 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
Use unified 4D association instead of the two-step per-view parsing then cross-view matching pipeline (ablation)Multi-person motion capture on Shelf · ShelfPCP Avg (%): 93.1 -> 97.6Improved
Add temporal tracking edges to the per-frame G3D association (ablation)Multi-person motion capture on Shelf · ShelfPCP Avg (%): 93.4 -> 97.6Improved
Use unified 4D association rather than Dong's methodMulti-person motion capture · Our testing datasetPrecision (%): 71.0 -> 88.5Improved
Use unified 4D association rather than Dong's methodMulti-person motion capture · Our testing datasetRecall (%): 80.2 -> 90.2Improved

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