Reducing Semantic Confusion: Scene-aware Aggregation Network for Remote Sensing Cross-modal Retrieval
Open paper
Benchmark
Model
Rank
Results
cross-modal-retrieval-on-rsicd
SWAN
#6
Mean Recall: 20.61%
Image-to-text R@1: 7.41%
text-to-image R@1: 5.56%
cross-modal-retrieval-on-rsitmd
SWAN
#7
Image-to-text R@1: 13.35%
Mean Recall: 34.11%
text-to-imageR@1: 11.24%
Rank counts only results with a code link.