Learning Deep Structure-Preserving Image-Text Embeddings
Open paper
Benchmark
Model
Rank
Results
image-retrieval-on-flickr30k-1k-test
SPE
–
R@1: 29.7
R@5: 60.1
R@10: 72.1
phrase-grounding-on-flickr30k-entities-test
DSPE
–
R@1: 43.89
R@5: 64.46
R@10: 68.66
Rank counts only results with a code link.