PTP-BLIP

Reported on 6 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.

Miscellaneous6 results

Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2022-12-19
69.7
best: 84.8 (BEiT-3)
Position-guided Text Prompt for Vision-Language Pre-training arXiv:2212.09737
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2022-12-19
94.7
best: 98.5 (X2-VLM (large))
Position-guided Text Prompt for Vision-Language Pre-training arXiv:2212.09737
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2022-12-19
90
best: 96.5 (X2-VLM (large))
Position-guided Text Prompt for Vision-Language Pre-training arXiv:2212.09737
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2022-12-19
49.5
best: 68 (VAST)
Position-guided Text Prompt for Vision-Language Pre-training arXiv:2212.09737
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2022-12-19
84.2
best: 92.8 (VAST)
Position-guided Text Prompt for Vision-Language Pre-training arXiv:2212.09737
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2022-12-19
75.9
best: 92.8 (BEiT-3)
Position-guided Text Prompt for Vision-Language Pre-training arXiv:2212.09737