AI Paper Atlas

Research map / Video / Video segmentation and tracking

Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement

Priyank Pathak, Yogesh S. Rawat

ICCV 2025 · Video › Video segmentation and tracking · approach: Spatial-temporal video person re-identification · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
add S2A self-attention instead of traditional self-attention (ablation)CSCI (EVA-02) · PRCC (CC protocol)Rank-1: 63.5 -> 66.2Improved
add S2A self-attention instead of masked self-attention (ablation)CSCI (EVA-02) · PRCC (CC protocol)Rank-1: 65.3 -> 66.2Improved
add S2A self-attention instead of masked self-attention (ablation)CSCI (EVA-02) · LTCC (CC protocol)Rank-1: 46.7 -> 47.8Improved
add S2A self-attention instead of traditional self-attention (ablation)CSCI (EVA-02) · LTCC (CC protocol)mAP: 23.5 -> 24.4Improved
add color token with S2A to EVA-02 baselineEVA-02 · LTCC (CC protocol)Rank-1: 44.9 -> 47.8Improved
add color token with S2A to EVA-02 baselineEVA-02 · PRCC (CC protocol)Rank-1: 61.6 -> 66.2Improved
add color disentanglement to video baseline EVA-02 + EZ-CLIPEVA-02 + EZ-CLIP · MeVID (General protocol)Rank-1: 76.6 -> 79.1Improved
add color disentanglement to video baseline EVA-02 + EZ-CLIPEVA-02 + EZ-CLIP · CCVID (CC protocol)Rank-1: 89.8 -> 90.8Improved
predict color with MSE loss instead of cosine loss (ablation)CSCI (EVA-02) · PRCC (CC protocol)Rank-1: 65.0 -> 66.2Improved
predict color vectors instead of feeding them as input (ablation)CSCI (EVA-02) · PRCC (CC protocol)Rank-1: 63.1 -> 66.2Improved
use color token instead of clothing-label head token (ablation)CSCI (EVA-02) · LTCC (CC protocol)Rank-1: 46.3 -> 47.8Improved
use color token instead of grey-scale augmentation (ablation)CSCI (EVA-02) · LTCC (CC protocol)Rank-1: 38.3 -> 47.8Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy