MIA

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· 2019-06-23
53.1
best: 77.62 (MARS)
SOTA
Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments arXiv:1906.09610
Text based Person RetrievalonCUHK-PEDES
R@10· 2019-06-23
82.9
best: 94.27 (MARS)
SOTA
Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments arXiv:1906.09610
Text based Person RetrievalonCUHK-PEDES
R@5· 2019-06-23
75
best: 90.63 (MARS)
SOTA
Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments arXiv:1906.09610