Cross-modal geo-localization on CORE Intercontinental-level Subset1 1.0 (v1.0)
77.44R@1MAPS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAPSQuery=Joint query2026.06 | 77.44 | 79.56 | |
| PMRLQuery=Joint query2026.06 | 75.02 | 77.46 | |
| GRAMQuery=Joint query2026.06 | 74.66 | 77.18 | |
| Pairwise alignmentQuery=Joint query2026.06 | 74.21 | 76.66 | |
| VASTQuery=Joint query2026.06 | 73.42 | 75.88 | |
| CLIP-L/14Query=Image only2026.06 | 66.29 | 68.84 | |
| BLIPQuery=Image only2026.06 | 65.76 | 68.39 | |
| CLIP-B/16Query=Image only2026.06 | 62.26 | 64.82 | |
| PLANET2026.03 | 57.9 | 60.72 | |
| PLANETQuery=Text only2026.06 | 57.9 | 60.72 | |
| CrossText2Loc2026.03 | 53.12 | 55.88 | |
| CrossText2LocQuery=Text only2026.06 | 53.12 | 55.88 | |
| Long-CLIP2026.03 | 52.78 | 55.34 | |
| EVA2-CLIPBackbone=L/142026.03 | 47.59 | 50.4 | |
| CLIPBackbone=L/142026.03 | 45.75 | 48.42 | |
| CLIP-L/14Query=Text only2026.06 | 45.75 | 48.42 | |
| BLIP2026.03 | 45.59 | 48.4 | |
| BLIPQuery=Text only2026.06 | 45.59 | 48.4 | |
| SigLIPBackbone=SO400M2026.03 | 45.03 | 47.74 | |
| RemoteCLIP2026.03 | 44.79 | 47.66 | |
| EVA2-CLIPBackbone=B/162026.03 | 42.18 | 44.74 | |
| CLIPBackbone=B/162026.03 | 42.18 | 44.74 | |
| CLIP-B/16Query=Text only2026.06 | 42.18 | 44.74 | |
| TAG-CLIP2026.03 | 38.15 | 40.78 | |
| X2-VLM2026.03 | 35.79 | 38.5 | |
| SigLIPBackbone=B/162026.03 | 29.13 | 31.87 | |
| X-VLM2026.03 | 28.9 | 30.65 | |
| ViLT2026.03 | 24.43 | 23.18 |