Research map / 3D vision / Human pose estimation
Improving Person Re-Identification via Pose-Aware Multi-Shot Matching
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 pose-aware multi-shot matching to KISSME | KISSME person re-identification · 3DPeS Set3 | Rank-1: 21.0 -> 68.4 | Helped |
| add pose-aware multi-shot matching to KISSME | KISSME person re-identification · 3DPeS Set4 | Rank-1: 25.0 -> 58.3 | Helped |
| add pose-aware multi-shot matching to KISSME | KISSME person re-identification · 3DPeS Set5 | Rank-1: 22.2 -> 55.6 | Helped |
| add pose-aware multi-shot matching to KISSME | KISSME person re-identification · 3DPeS Set All | Rank-1: 26.5 -> 59.2 | Helped |
| add pose-aware multi-shot matching to KISSME | KISSME person re-identification · iLIDS-Vid | Rank-1: 11.3 -> 30.3 | No clear effect |
| add pose-aware multi-shot matching to KISSME | KISSME person re-identification · PRID 2011 | Rank-1: 22.3 -> 45.0; 56.5 | Mixed |
| add sample selection based on sample confidence (ablation) | PaMM · 3DPeS Set3 | AUC: 95.3 -> 96.4 | Helped |
| add sample selection based on sample confidence (ablation) | PaMM · 3DPeS Set4 | AUC: 87.2 -> 88.9 | Helped |
| add sample selection based on sample confidence (ablation) | PaMM · 3DPeS Set5 | AUC: 89.5 -> 88.6 | No clear effect |
| add sample selection based on sample confidence (ablation) | PaMM · 3DPeS Set All | AUC: 92.7 -> 94.1 | Helped |
| train pose-pair matching weights instead of using uniform weights (ablation) | PaMM · 3DPeS Set3 | AUC: 95.6 -> 96.4 | Helped |
| train pose-pair matching weights instead of using uniform weights (ablation) | PaMM · 3DPeS Set4 | AUC: 88.9 -> 88.9 | No clear effect |
Closest papers by meaning
- A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-Ranking (CVPR 2018 · similarity 0.89)
- Pose-guided Enriched Feature Learning for Federated-by-camera Person Re-identification (CVPR 2026 · similarity 0.88)
- Similarity Learning With Spatial Constraints for Person Re-Identification (CVPR 2016 · similarity 0.88)
- Top-Push Video-Based Person Re-Identification (CVPR 2016 · similarity 0.88)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · similarity 0.86)
- Exploring the Camera Bias of Person Re-identification (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.