Research map / Video / Video segmentation and tracking
Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement
Priyank Pathak, Yogesh S. Rawat
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 S2A self-attention instead of traditional self-attention (ablation) | CSCI (EVA-02) · PRCC (CC protocol) | Rank-1: 63.5 -> 66.2 | Improved |
| add S2A self-attention instead of masked self-attention (ablation) | CSCI (EVA-02) · PRCC (CC protocol) | Rank-1: 65.3 -> 66.2 | Improved |
| add S2A self-attention instead of masked self-attention (ablation) | CSCI (EVA-02) · LTCC (CC protocol) | Rank-1: 46.7 -> 47.8 | Improved |
| add S2A self-attention instead of traditional self-attention (ablation) | CSCI (EVA-02) · LTCC (CC protocol) | mAP: 23.5 -> 24.4 | Improved |
| add color token with S2A to EVA-02 baseline | EVA-02 · LTCC (CC protocol) | Rank-1: 44.9 -> 47.8 | Improved |
| add color token with S2A to EVA-02 baseline | EVA-02 · PRCC (CC protocol) | Rank-1: 61.6 -> 66.2 | Improved |
| add color disentanglement to video baseline EVA-02 + EZ-CLIP | EVA-02 + EZ-CLIP · MeVID (General protocol) | Rank-1: 76.6 -> 79.1 | Improved |
| add color disentanglement to video baseline EVA-02 + EZ-CLIP | EVA-02 + EZ-CLIP · CCVID (CC protocol) | Rank-1: 89.8 -> 90.8 | Improved |
| predict color with MSE loss instead of cosine loss (ablation) | CSCI (EVA-02) · PRCC (CC protocol) | Rank-1: 65.0 -> 66.2 | Improved |
| predict color vectors instead of feeding them as input (ablation) | CSCI (EVA-02) · PRCC (CC protocol) | Rank-1: 63.1 -> 66.2 | Improved |
| use color token instead of clothing-label head token (ablation) | CSCI (EVA-02) · LTCC (CC protocol) | Rank-1: 46.3 -> 47.8 | Improved |
| use color token instead of grey-scale augmentation (ablation) | CSCI (EVA-02) · LTCC (CC protocol) | Rank-1: 38.3 -> 47.8 | Improved |
Closest papers by meaning
- Identity-Clothing Similarity Modeling for Unsupervised Clothing Change Person Re-Identification (CVPR 2025 · similarity 0.87)
- CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification (ECCV 2026 · similarity 0.86)
- CGCC: Towards Generalizable Clothes-Changing Person Re-Identification (ECCV 2026 · similarity 0.86)
- DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID (CVPR 2025 · similarity 0.85)
- Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions (CVPR 2024 · similarity 0.84)
- TOP-ReID: Multi-Spectral Object Re-identification with Token Permutation (AAAI 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.
