CLIP-ReID (with re-ranking)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Person Re-IdentificationonMSMT17
Rank-1· 2022-11-25
91.2
best: 91.7 (SOLIDER (with re-ranking))
SOTA
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Person Re-IdentificationonMSMT17
mAP· 2022-11-25
86.7
SOTA
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977