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/P2-Net (triplet loss)

P2-Net (triplet loss)

Reported on 7 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 Vision7 results

Person Re-IdentificationonDukeMTMC-reID
Rank-10· 2019-10-22
95
best: 97.9 (CTL Model (ResNet50, 256x128))
SOTA
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification arXiv:1910.10111
Person Re-IdentificationonDukeMTMC-reID
Rank-5· 2019-10-22
93.1
best: 96.5 (Viewpoint-Aware Loss(RK))
SOTA
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification arXiv:1910.10111
Person Re-IdentificationonMarket-1501
Rank-1· 2019-10-22
95.2
best: 98 (st-ReID(RE, RK))
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification arXiv:1910.10111
Person Re-IdentificationonMarket-1501
Rank-5· 2019-10-22
98.2
best: 98.9 (st-ReID(RE, RK))
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification arXiv:1910.10111
Person Re-IdentificationonMarket-1501
mAP· 2019-10-22
85.6
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification arXiv:1910.10111
Person Re-IdentificationonDukeMTMC-reID
Rank-1· 2019-10-22
86.5
best: 95.6 (CTL Model (ResNet50, 256x128))
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification arXiv:1910.10111
Person Re-IdentificationonDukeMTMC-reID
mAP· 2019-10-22
73.1
best: 97.1 (DenseIL)
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification arXiv:1910.10111