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/TMGF

TMGF

Reported on 12 benchmarks across 1 task · 1 paper · 4 SOTA

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

Computer Vision12 results

Person Re-IdentificationonDukeMTMC-reID
MAP· 2022-11-22
76.8
SOTA
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonMSMT17
Rank-10· 2022-11-22
92.1
best: 96 (PCL-CLIP (L_pcl+L_id))
SOTA
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonMSMT17
Rank-5· 2022-11-22
90.2
best: 94.7 (PCL-CLIP (L_pcl+L_id))
SOTA
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonMarket-1501
Rank-10· 2022-11-22
98.7
SOTA
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonDukeMTMC-reID
Rank-1· 2022-11-22
86.7
best: 95.6 (CTL Model (ResNet50, 256x128))
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonDukeMTMC-reID
Rank-10· 2022-11-22
94.1
best: 97.9 (CTL Model (ResNet50, 256x128))
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonDukeMTMC-reID
Rank-5· 2022-11-22
92.9
best: 96.5 (Viewpoint-Aware Loss(RK))
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonMSMT17
Rank-1· 2022-11-22
83.3
best: 91.7 (SOLIDER (with re-ranking))
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonMSMT17
mAP· 2022-11-22
58.2
best: 86.7 (CLIP-ReID (with re-ranking))
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonMarket-1501
MAP· 2022-11-22
89.5
best: 89.6 (TransReID-SSL (ViTi-S))
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonMarket-1501
Rank-1· 2022-11-22
95.5
best: 98 (st-ReID(RE, RK))
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280
Person Re-IdentificationonMarket-1501
Rank-5· 2022-11-22
98
best: 98.9 (st-ReID(RE, RK))
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification arXiv:2211.12280