Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models

Benchmark Model Rank Results
image-retrieval-on-flickr30k-1k-testHGLMM FV#14R@1: 24.7R@5: 53.4R@10: 66.8
phrase-grounding-on-flickr30k-entities-testCCA - Fast RCNN#13R@1: 41.77R@5: 64.52R@10: 70.77
phrase-grounding-on-flickr30k-entities-testCCA - VGG19#14R@1: 30.83R@5: 58.01R@10: 67.15
phrase-grounding-on-flickr30k-entities-testCCA#16R@1: 25.30R@10: 59.66