MGN (ACM MM'18)

Reported on 4 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 Vision4 results

Person Re-IdentificationonCUHK03 detected
MAP· 2018-04-04
66
best: 86.9 (Top-DB-Net + RK)
SOTA
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
Person Re-IdentificationonCUHK03 detected
Rank-1· 2018-04-04
68
best: 85.7 (Top-DB-Net + RK)
SOTA
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
Person Re-IdentificationonCUHK03 labeled
MAP· 2018-04-04
67.4
best: 89.29 (Weakly Pre-training (ResNet101+RK))
SOTA
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
Person Re-IdentificationonCUHK03 labeled
Rank-1· 2018-04-04
68
best: 87.86 (Weakly Pre-training (ResNet101+RK))
SOTA
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438