Global–Local Information Soft-Alignment for Cross-Modal Remote-Sensing Image–Text Retrieval
Open paper
Benchmark
Model
Rank
Results
cross-modal-retrieval-on-rsicd
GLISA
–
Mean Recall: 37.69%
Image-to-text R@1: 20.68%
text-to-image R@1: 14.73%
cross-modal-retrieval-on-rsitmd
GLISA
–
Image-to-text R@1: 32.08%
Mean Recall: 50.69%
text-to-imageR@1: 23.36%
Rank counts only results with a code link.