ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval

Open paper
Benchmark Model Rank Results
cross-modal-retrieval-on-coco-2014ViSTA–Text-to-image R@1: 52.6Text-to-image R@5: 79.6…
cross-modal-retrieval-on-flickr30kViSTA–Image-to-text R@1: 89.5Image-to-text R@5: 98.4…

Rank counts only results with a code link.