AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

CGCC: Towards Generalizable Clothes-Changing Person Re-Identification

Yizhi Wu, Fangyi Liu, wei yu, Mang Ye

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 0 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 BGPA (biometric-guided prototype alignment) (ablation)EVA02-CLIP baseline · CGCC -> PRCCRank-1: 54.5 -> 56.4Improved
add SAOP (spectrum-aware orthogonal projection) (ablation)EVA02-CLIP baseline · CGCC -> PRCCRank-1: 54.5 -> 59.0Improved
add both BGPA and SAOP (ablation)EVA02-CLIP baseline · CGCC -> PRCCRank-1: 54.5 -> 62.0Improved
add both BGPA and SAOP (ablation)EVA02-CLIP baseline · CGCC -> PRCCmAP: 50.6 -> 56.9Improved
add SAOP on top of BGPA (ablation)TGIR · CGCC -> PRCCRank-1: 56.4 -> 62.0Improved
train on CGCC instead of LaSTMADE · DEEP targetRank-1: 51.4 -> 59.6Improved
train on CGCC instead of DEEPCAL · LTCC targetRank-1: 13.0 -> 19.4Improved
train on CGCC instead of DEEPEVA02-CLIP · LTCC targetRank-1: 31.6 -> 37.2Improved
train on CGCC instead of LaSTEVA02-CLIP · PRCC targetRank-1: 55.5 -> 54.5Hurt
train on CGCC instead of LaSTTransReID · LTCC targetRank-1: 12.2 -> 21.9Improved
use TGIR instead of MADE on CGCC-trained modelsMADE · average over LTCC/PRCC/DEEPRank-1: 52.7 -> 54.8Improved
use TGIR instead of Differ on CGCC-trained modelsDiffer · average over LTCC/PRCC/DEEPRank-1: 49.8 -> 54.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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