Visual Grounding On Refcoco Val
Metriken
Accuracy (%)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy (%) |
|---|---|
| multi-grained-vision-language-pre-training | 84.51 |
| x-2-vlm-all-in-one-pre-trained-model-for | 85.2 |
| toward-building-general-foundation-models-for | 86.1 |
| mplug-2-a-modularized-multi-modal-foundation | 90.33 |
| x-2-vlm-all-in-one-pre-trained-model-for | 87.6 |
| florence-2-advancing-a-unified-representation | 93.4 |