Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CLIP-ReID (without re-ranking)

CLIP-ReID (without re-ranking)

Reported on 14 benchmarks across 3 tasks · 1 paper

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

Computer Vision14 results

Person Re-IdentificationonMSMT17
Rank-1· 2022-11-25
89.7
best: 91.7 (SOLIDER (with re-ranking))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Person Re-IdentificationonMSMT17
mAP· 2022-11-25
75.8
best: 86.7 (CLIP-ReID (with re-ranking))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Person Re-IdentificationonMarket-1501
Rank-1· 2022-11-25
95.4
best: 98 (st-ReID(RE, RK))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Person Re-IdentificationonMarket-1501
mAP· 2022-11-25
90.5
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Person Re-IdentificationonDukeMTMC-reID
Rank-1· 2022-11-25
90.8
best: 95.6 (CTL Model (ResNet50, 256x128))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Person Re-IdentificationonDukeMTMC-reID
mAP· 2022-11-25
83.1
best: 97.1 (DenseIL)
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Intelligent SurveillanceonVeRi-776
Rank-1· 2022-11-25
97.3
best: 98 (MBR4B-LAI (w/ RK))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Intelligent SurveillanceonVeRi-776
mAP· 2022-11-25
84.5
best: 92.1 (MBR4B-LAI (w/ RK))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Intelligent SurveillanceonVehicleID Small
Rank-1· 2022-11-25
85.5
best: 96.2 (Recall@k Surrogate loss (ViT-B/16))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Intelligent SurveillanceonVehicleID Small
Rank-5· 2022-11-25
97.2
best: 98 (Recall@k Surrogate loss (ViT-B/16))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Vehicle Re-IdentificationonVeRi-776
Rank-1· 2022-11-25
97.3
best: 98 (MBR4B-LAI (w/ RK))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Vehicle Re-IdentificationonVeRi-776
mAP· 2022-11-25
84.5
best: 92.1 (MBR4B-LAI (w/ RK))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Vehicle Re-IdentificationonVehicleID Small
Rank-1· 2022-11-25
85.5
best: 96.2 (Recall@k Surrogate loss (ViT-B/16))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977
Vehicle Re-IdentificationonVehicleID Small
Rank-5· 2022-11-25
97.2
best: 98 (Recall@k Surrogate loss (ViT-B/16))
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels arXiv:2211.13977