GPS Embeddings
GPS Embeddings is the collective name for a set of feature-learning techniques where GPS coordinates are mapped to vectors of real numbers.
Papers
No papers found.
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | GeoCLIP | mAP | 0.36 | — | Unverified |
| 2 | GPS2Vec+ | mAP | 0.35 | — | Unverified |
| 3 | Liao et al. | mAP | 0.35 | — | Unverified |
| 4 | GPS2Vec | mAP | 0.3 | — | Unverified |
| 5 | GPS2Vec onehot | mAP | 0.28 | — | Unverified |
| 6 | HashTag | mAP | 0.26 | — | Unverified |
| 7 | TagFeature | mAP | 0.26 | — | Unverified |
| 8 | OneHot | mAP | 0.24 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | GeoCLIP | mAP | 0.25 | — | Unverified |
| 2 | GPS2Vec+ | mAP | 0.21 | — | Unverified |
| 3 | GPS2Vec | mAP | 0.18 | — | Unverified |
| 4 | HashTag | mAP | 0.16 | — | Unverified |
| 5 | TagFeature | mAP | 0.16 | — | Unverified |
| 6 | GPS2Vec onehot | mAP | 0.13 | — | Unverified |
| 7 | OneHot | mAP | 0.07 | — | Unverified |