| Benchmark | Model | Rank | Results |
|---|---|---|---|
| cross-modal-retrieval-on-rsicd | RemoteCLIP | #3 | Mean Recall: 36.35%Image-to-text R@1: 18.39%text-to-image R@1: 14.73% |
| cross-modal-retrieval-on-rsitmd | RemoteCLIP | #3 | Image-to-text R@1: 28.76%Mean Recall: 50.52%text-to-imageR@1: 23.76% |