Research map / 3D vision / Depth and stereo
Cross-View People Tracking by Scene-Centered Spatio-Temporal Parsing
Yuanlu Xu, Xiaobai Liu, Lei Qin, Song-Chun Zhu
Read the paperCheck 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 |
|---|---|---|---|
| add motion and pose/action semantic attributes to appearance and geometry (ablation) | ST-APG tracker · PPL-DA Seq-Court | TA (%): 26.82 -> 34.47 | Improved |
| add motion and pose/action semantic attributes to appearance and geometry (ablation) | ST-APG tracker · PPL-DA Seq-Office | TA (%): 39.79 -> 47.38 | Improved |
| add motion and pose/action semantic attributes to appearance and geometry (ablation) | ST-APG tracker · PPL-DA Seq-Plaza | TA (%): 20.59 -> 25.18 | Improved |
| add motion and pose/action semantic attributes to appearance and geometry (ablation) | ST-APG tracker · PPL-DA Seq-Court | IDSW: 114 -> 79 | Improved |
| add motion and pose/action semantic attributes to appearance and geometry (ablation) | ST-APG tracker · PPL-DA Seq-Plaza | IDSW: 244 -> 165 | Improved |
| associate tracklets instead of bounding boxes | multi-view tracking · PPL-DA Seq-Court | TA (%): 22.26 -> 34.47 | Improved |
| use ST-APG instead of HTC | multi-view tracking · PPL-DA Seq-Office | TA (%): 41.17 -> 47.38 | Improved |
| use ST-APG instead of HTC | multi-view tracking · PPL-DA Seq-Plaza | IDSW: 202 -> 165 | Improved |
Closest papers by meaning
- DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes (IJCV 2023 · similarity 0.87)
- Visio-Temporal Attention for Multi-Camera Multi-Target Association (ICCV 2021 · similarity 0.86)
- Multiple Human Association and Tracking from Egocentric and Complementary Top Views (TPAMI 2021 · similarity 0.86)
- Contextualized Trajectory Parsing with Spatio-Temporal Graph (TPAMI 2024 · similarity 0.86)
- Scene-Centric Joint Parsing of Cross-View Videos (AAAI 2018 · similarity 0.85)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.84)
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.
