PLIP-RN50

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 RetrievalonICFG-PEDES
R@1· 2023-05-15
64.25
best: 68.51 (APTM)
SOTA
PLIP: Language-Image Pre-training for Person Representation Learning arXiv:2305.08386
Text based Person RetrievalonICFG-PEDES
R@10· 2023-05-15
86.32
best: 87.53 (Filtering-WoRA(Small))
SOTA
PLIP: Language-Image Pre-training for Person Representation Learning arXiv:2305.08386
Text based Person RetrievalonICFG-PEDES
R@5· 2023-05-15
80.88
best: 83.1 (Filtering-WoRA(Small))
SOTA
PLIP: Language-Image Pre-training for Person Representation Learning arXiv:2305.08386