Visual Grounding On Refcoco Test B
Metrics
Accuracy (%)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy (%) |
|---|---|
| toward-building-general-foundation-models-for | 79.8 |
| x-2-vlm-all-in-one-pre-trained-model-for | 78.4 |
| mplug-2-a-modularized-multi-modal-foundation | 86.05 |
| multi-grained-vision-language-pre-training | 76.91 |
| florence-2-advancing-a-unified-representation | 92.0 |
| x-2-vlm-all-in-one-pre-trained-model-for | 81.8 |