IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval
Open paper
Benchmark
Model
Rank
Results
cross-modal-retrieval-on-coco-2014
IMRAM
#27
Text-to-image R@1: 39.7
Text-to-image R@5: 69.1
…
cross-modal-retrieval-on-flickr30k
IMRAM
#16
Image-to-text R@1: 74.1
Image-to-text R@5: 93.0
…
Rank counts only results with a code link.