AXM-Net

Reported on 4 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 Vision4 results

Text based Person RetrievalonCUHK-PEDES
R@1· 2021-01-19
61.9
best: 77.62 (MARS)
SOTA
AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification arXiv:2101.08238
Text based Person RetrievalonCUHK-PEDES
mAP· 2021-01-19
57.38
best: 71.41 (MARS)
SOTA
AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification arXiv:2101.08238
Text based Person RetrievalonCUHK-PEDES
R@10· 2021-01-19
85.75
best: 94.27 (MARS)
AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification arXiv:2101.08238
Text based Person RetrievalonCUHK-PEDES
R@5· 2021-01-19
79.4
best: 90.63 (MARS)
AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification arXiv:2101.08238