Research map / Label-efficient and robust learning / Recognition and long-tail
Clothing Status Awareness for Long-Term Person Re-Identification
Yan Huang, Qiang Wu, JingSong Xu, Yi Zhong, ZhaoXiang Zhang
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 identity loss Lid to ICE (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 41.4 -> 52.0 | Improved |
| add Lcit loss to ICE (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 49.9 -> 52.0 | Improved |
| use MPM (2 vertical slices, GAP+GMP) instead of no slice division (ablation) | ICE · Celeb-reID | rank-1 accuracy (%): 50.6 -> 52.0 | Improved |
| use GAP+GMP with 2 vertical slices instead of GMP only (LMP) (ablation) | ICE · Celeb-reID | rank-1 accuracy (%): 51.0 -> 52.0 | Improved |
| add domain adaptation module DAM in ICR (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 54.8 -> 55.6 | Improved |
| add Lsim cos in feature regularization (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 53.0 -> 55.6 | Improved |
| add Ldis cos in feature regularization (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 52.5 -> 55.6 | Improved |
| add ICR regularization (FRM) to ICE training (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 52.0 -> 55.6 | Improved |
| use only fid for inference instead of fap + fid (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 16.4 -> 55.6 | Improved |
| DenseNet-121 backbone instead of ResNet-50 (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 54.9 -> 55.6 | Improved |
| train on Celeb-reID-light without no-clothing-change cases (ablation) | RCSANet · Celeb-reID | rank-1 accuracy (%): 55.6 -> 50.4 | Hurt |
| train on Celeb-reID-light without no-clothing-change cases (ablation) | ReIDCaps · Celeb-reID | rank-1 accuracy (%): 51.2 -> 41.8 | Hurt |
Closest papers by meaning
- Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification (ICCV 2023 · similarity 0.89)
- CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification (ECCV 2026 · similarity 0.88)
- Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions (CVPR 2024 · similarity 0.85)
- Identity-Clothing Similarity Modeling for Unsupervised Clothing Change Person Re-Identification (CVPR 2025 · similarity 0.84)
- DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID (CVPR 2025 · similarity 0.84)
- Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification (CVPR 2024 · similarity 0.83)
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.
