ViTAA

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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

Computer Vision3 results

Text based Person RetrievalonCUHK-PEDES
R@1· 2020-05-15
55.97
best: 77.62 (MARS)
SOTA
ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language arXiv:2005.07327
Text based Person RetrievalonCUHK-PEDES
R@10· 2020-05-15
83.52
best: 94.27 (MARS)
SOTA
ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language arXiv:2005.07327
Text based Person RetrievalonCUHK-PEDES
R@5· 2020-05-15
75.84
best: 90.63 (MARS)
SOTA
ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language arXiv:2005.07327