Research map / Label-efficient and robust learning / Recognition and long-tail
Norm-Aware Embedding for Efficient Person Search
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 |
|---|---|---|---|
| Decompose embeddings into a detection norm and identity angle | One-step person search · CUHK-SYSU | mAP: 84.4 -> 91.5 | Helped |
| Decompose embeddings into a detection norm and identity angle | One-step person search · PRW | mAP: 34.0 -> 43.3 | Helped |
| Add pixel-wise norm-aware feature weighting (ablation) | NAE · CUHK-SYSU | mAP: 91.5 -> 92.1 | Helped |
| Add pixel-wise norm-aware feature weighting (ablation) | NAE · PRW | mAP: 43.3 -> 44.0 | Helped |
| Add Class Weighted Similarity (ablation) | OIM-base · CUHK-SYSU | mAP: 84.4 -> 87.1 (+2.7) | Helped |
| Add Class Weighted Similarity (ablation) | OIM-base · CUHK-SYSU | top-1: 86.1 -> 88.5 (+2.4) | Helped |
| Remove the CWS scale operation (ablation) | NAE · CUHK-SYSU | mAP: 91.5 -> 89.9 (-1.6) | Hurt |
| Remove the CWS scale operation (ablation) | NAE · CUHK-SYSU | top-1: 92.4 -> 91.3 (-1.1) | Hurt |
Closest papers by meaning
- A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-Ranking (CVPR 2018 · similarity 0.89)
- Hierarchical Online Instance Matching for Person Search (AAAI 2020 · similarity 0.89)
- Resource Aware Person Re-Identification Across Multiple Resolutions (CVPR 2018 · similarity 0.88)
- Joint Detection and Identification Feature Learning for Person Search (CVPR 2017 · similarity 0.88)
- Divide and Conquer: Hybrid Pre-training for Person Search (AAAI 2024 · similarity 0.87)
- Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification (CVPR 2025 · similarity 0.86)
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.