Cross-modal Geo-localization on CVG-Text (Brisbane)
86.17Recall@1MAPS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MAPSQuery=Joint query2026.06 | 86.17 | 88.42 | |
| Pairwise alignmentQuery=Joint query2026.06 | 82.17 | 85.08 | |
| PMRLQuery=Joint query2026.06 | 81.05 | 84.11 | |
| GRAMQuery=Joint query2026.06 | 80.58 | 83.64 | |
| VASTQuery=Joint query2026.06 | 79.64 | 82.7 | |
| CLIP-L/14Query=Image only2026.06 | 74.25 | 77.5 | |
| BLIPQuery=Image only2026.06 | 73.08 | 76.08 | |
| CLIP-B/16Query=Image only2026.06 | 68.92 | 71.83 | |
| PLANET2026.03 | 49.83 | 53.67 | |
| PLANETQuery=Text only2026.06 | 49.83 | 53.67 | |
| CrossText2Loc2026.03 | 47.58 | 51.8 | |
| CrossText2LocQuery=Text only2026.06 | 47.58 | 51.8 | |
| Long-CLIP2026.03 | 46.75 | 48.17 | |
| EVA2-CLIP-L/142026.03 | 35.67 | 38 | |
| BLIP2026.03 | 34.5 | 38.17 | |
| BLIPQuery=Text only2026.06 | 34.5 | 38.17 | |
| SigLIP-SO400M2026.03 | 34.25 | 36.83 | |
| CLIP-L/142026.03 | 34.08 | 37.25 | |
| CLIP-L/14Query=Text only2026.06 | 34.08 | 37.25 | |
| RemoteCLIP2026.03 | 32.92 | 34.75 | |
| CLIP-B/162026.03 | 29.92 | 32.58 | |
| CLIP-B/16Query=Text only2026.06 | 29.92 | 32.58 | |
| TAG-CLIP2026.03 | 29.83 | 31.75 | |
| EVA2-CLIP-B/162026.03 | 28.42 | 31.75 | |
| X2-VLM2026.03 | 21.58 | 23.67 | |
| SigLIP-B/162026.03 | 19.58 | 22 | |
| X-VLM2026.03 | 15.67 | 17.6 | |
| ViLT2026.03 | 11.1 | 14.5 |