Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
Open paper
Benchmark
Model
Rank
Results
cross-modal-retrieval-on-rsicd
DOVE
–
Mean Recall: 22.72%
Image-to-text R@1: 8.66%
text-to-image R@1: 6.04%
cross-modal-retrieval-on-rsitmd
DOVE
–
Image-to-text R@1: 16.81%
Mean Recall: 37.73%
text-to-imageR@1: 12.20%
Rank counts only results with a code link.