Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders
Open paper
Benchmark
Model
Rank
Results
image-retrieval-on-flickr30k-1k-test
TERAN MrSw
#6
R@1: 56.5
R@5: 81.2
R@10: 88.2
image-retrieval-on-flickr30k-1k-test
TERAN Symm.
#7
R@1: 55.7
R@5: 83.1
R@10: 89.3
Rank counts only results with a code link.