VGSG (ViT-Base)

Reported on 3 benchmarks across 1 task · 1 paper

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· 2023-11-13
63.05
best: 68.51 (APTM)
VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search arXiv:2311.07514
Text based Person RetrievalonICFG-PEDES
R@10· 2023-11-13
84.36
best: 87.53 (Filtering-WoRA(Small))
VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search arXiv:2311.07514
Text based Person RetrievalonICFG-PEDES
R@5· 2023-11-13
78.43
best: 83.1 (Filtering-WoRA(Small))
VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search arXiv:2311.07514