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/PCB-PAST

PCB-PAST

Reported on 8 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Methodology4 results

Domain AdaptationonMarket to Duke
mAP· 2019-07-31
54.3
best: 74.8 (CORE-ReID)
SOTA
Self-training with progressive augmentation for unsupervised cross-domain person re-identification arXiv:1907.13315
Domain AdaptationonMarket to Duke
rank-1· 2019-07-31
72.4
best: 85 (CCTSE)
Self-training with progressive augmentation for unsupervised cross-domain person re-identification arXiv:1907.13315
Domain AdaptationonDuke to Market
mAP· 2019-07-31
54.6
best: 84.4 (CORE-ReID)
Self-training with progressive augmentation for unsupervised cross-domain person re-identification arXiv:1907.13315
Domain AdaptationonDuke to Market
rank-1· 2019-07-31
78.4
best: 93.6 (CORE-ReID)
Self-training with progressive augmentation for unsupervised cross-domain person re-identification arXiv:1907.13315

Other4 results

Unsupervised Domain AdaptationonMarket to Duke
mAP· 2019-07-31
54.3
best: 74.8 (CORE-ReID)
SOTA
Self-training with progressive augmentation for unsupervised cross-domain person re-identification arXiv:1907.13315
Unsupervised Domain AdaptationonMarket to Duke
rank-1· 2019-07-31
72.4
best: 85 (CCTSE)
Self-training with progressive augmentation for unsupervised cross-domain person re-identification arXiv:1907.13315
Unsupervised Domain AdaptationonDuke to Market
mAP· 2019-07-31
54.6
best: 84.4 (CORE-ReID)
Self-training with progressive augmentation for unsupervised cross-domain person re-identification arXiv:1907.13315
Unsupervised Domain AdaptationonDuke to Market
rank-1· 2019-07-31
78.4
best: 93.6 (CORE-ReID)
Self-training with progressive augmentation for unsupervised cross-domain person re-identification arXiv:1907.13315