Cross-modal geo-localization on CORE Intercontinental-level Subset3 1.0
64.38R@1MAPS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAPSQuery=Joint query2026.06 | 64.38 | 69.05 | |
| PMRLQuery=Joint query2026.06 | 62.42 | 66.82 | |
| GRAMQuery=Joint query2026.06 | 62.18 | 66.55 | |
| Pairwise alignmentQuery=Joint query2026.06 | 62.05 | 66.86 | |
| VASTQuery=Joint query2026.06 | 61.57 | 65.9 | |
| CLIP-L/14Query=Image only2026.06 | 57.58 | 62.38 | |
| BLIPQuery=Image only2026.06 | 56.22 | 60.83 | |
| CLIP-B/16Query=Image only2026.06 | 53.37 | 57.95 | |
| PLANET2026.03 | 49.81 | 54.13 | |
| PLANETQuery=Text only2026.06 | 49.81 | 54.13 | |
| CrossText2Loc2026.03 | 46.97 | 51.27 | |
| CrossText2LocQuery=Text only2026.06 | 46.97 | 51.27 | |
| Long-CLIP2026.03 | 45.4 | 50.5 | |
| CLIPBackbone=L/142026.03 | 41.48 | 46.56 | |
| CLIP-L/14Query=Text only2026.06 | 41.48 | 46.56 | |
| EVA2-CLIPBackbone=L/142026.03 | 41.03 | 46.31 | |
| SigLIPBackbone=SO400M2026.03 | 40.71 | 46.15 | |
| RemoteCLIP2026.03 | 40.55 | 45.78 | |
| BLIP2026.03 | 39.77 | 44.66 | |
| BLIPQuery=Text only2026.06 | 39.77 | 44.66 | |
| EVA2-CLIPBackbone=B/162026.03 | 37.32 | 42.37 | |
| CLIPBackbone=B/162026.03 | 37.32 | 42.37 | |
| TAG-CLIP2026.03 | 37.32 | 42.37 | |
| CLIP-B/16Query=Text only2026.06 | 37.32 | 42.37 | |
| X2-VLM2026.03 | 36.12 | 41.25 | |
| SigLIPBackbone=B/162026.03 | 31.23 | 36.18 | |
| X-VLM2026.03 | 28.67 | 33.86 | |
| ViLT2026.03 | 25.58 | 30.79 |