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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use unified 4D association instead of the two-step per-view parsing then cross-view matching pipeline (ablation) | Multi-person motion capture on Shelf · Shelf | PCP Avg (%): 93.1 -> 97.6 | Improved |
| Add temporal tracking edges to the per-frame G3D association (ablation) | Multi-person motion capture on Shelf · Shelf | PCP Avg (%): 93.4 -> 97.6 | Improved |
| Use unified 4D association rather than Dong's method | Multi-person motion capture · Our testing dataset | Precision (%): 71.0 -> 88.5 | Improved |
| Use unified 4D association rather than Dong's method | Multi-person motion capture · Our testing dataset | Recall (%): 80.2 -> 90.2 | Improved |
Closest papers by meaning
- Self-supervised Multi-view Person Association and Its Applications (TPAMI 2020 · similarity 0.86)
- Fast and Robust Multi-Person 3D Pose Estimation and Tracking From Multiple Views (TPAMI 2021 · similarity 0.86)
- Real-Time Multi-person Motion Capture from Multi-view Video and IMUs (IJCV 2019 · similarity 0.86)
- PoseTrack: Joint Multi-Person Pose Estimation and Tracking (CVPR 2017 · similarity 0.86)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.85)
- CoMotion: Concurrent Multi-person 3D Motion (ICLR 2025 · similarity 0.85)
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.
