Research map / 3D vision / Human pose estimation
Cross-View Person Identification by Matching Human Poses Estimated With Confidence on Each Body Joint
Guoqiang Liang, Xuguang Lan, Kang Zheng, Song Wang, Nanning Zheng
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 fused joint confidence weighting (ablation) | pose matching · SEQ1 | CMC Rank-1 (%): 12.81 -> 30.00 | Improved |
| add fused joint confidence weighting (ablation) | pose matching · SEQ2 | CMC Rank-1 (%): 18.64 -> 29.55 | Improved |
| add fused joint confidence weighting (ablation) | pose matching · SYN | CMC Rank-1 (%): 52.50 -> 63.65 | Improved |
| add 2D confidence only (ablation) | pose matching · SEQ1 | CMC Rank-1 (%): 12.81 -> 25.26 | Improved |
| add 3D confidence only (ablation) | pose matching · SEQ1 | CMC Rank-1 (%): 12.81 -> 22.98 | Improved |
| add temporal confidence only (ablation) | pose matching · SEQ1 | CMC Rank-1 (%): 12.81 -> 22.46 | Improved |
| fused confidence instead of 2D confidence alone (ablation) | pose matching · SEQ2 | CMC Rank-1 (%): 30.68 -> 29.55 | Mixed |
| add pose (CPose) to Flow+RFA | Flow+RFA · SEQ1 | CMC Rank-1 (%): 87.02 -> 91.75 | Improved |
| add pose (CPose) to Flow+RFA | Flow+RFA · SYN | CMC Rank-1 (%): 82.12 -> 91.54 | Improved |
| add pose to RFA | RFA · SEQ1 | CMC Rank-1 (%): 68.42 -> 84.56 | Improved |
| add pose to RFA | RFA · SEQ2 | CMC Rank-1 (%): 69.77 -> 77.05 | Improved |
| confidence-weighted unsupervised pose vs supervised Flow on cross-dataset test | Flow · SEQ2 cross-dataset | CMC Rank-1 (%): 11.36 -> 29.55 | Improved |
Closest papers by meaning
- Learning View-Invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras (ICCV 2017 · similarity 0.90)
- Cross-View Tracking for Multi-Human 3D Pose Estimation at Over 100 FPS (CVPR 2020 · similarity 0.87)
- Fast and Robust Multi-Person 3D Pose Estimation From Multiple Views (CVPR 2019 · similarity 0.86)
- Fast and Robust Multi-Person 3D Pose Estimation and Tracking From Multiple Views (TPAMI 2021 · similarity 0.86)
- Shape-Aware Multi-Person Pose Estimation From Multi-View Images (ICCV 2021 · similarity 0.85)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 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.
