Deep Cross-Modal Projection Learning for Image-Text Matching
Open paper
Benchmark
Model
Rank
Results
nlp-based-person-retrival-on-cuhk-pedes
CMPM+CMPC
#14
R@1: 49.37
R@10: 79.27
cross-modal-retrieval-on-flickr30k
CMPL (ResNet)
#24
Image-to-text R@1: 49.6
Image-to-text R@5: 76.8
…
Rank counts only results with a code link.