Visual Grounding on RefMFAD RGBT-Ground (val)
0.6783Acc@0.5RGBT-VGNet
Evaluation results
| Method | Links | |
|---|---|---|
| RGBT-VGNetBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 0.6783 | |
| MV-HiVG-BBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 0.6707 | |
| MV-OneRef-LBackbone=BEIT3-L / BEIT3-L, Modality=RGB+TIR2025.12 | 0.6457 | |
| MV-HiVG-LBackbone=CLIP-L / CLIP-L, Modality=RGB+TIR2025.12 | 0.6178 | |
| MV-OneRef-BBackbone=BEIT3-B / BEIT3-B, Modality=RGB+TIR2025.12 | 0.6162 | |
| MV-D-MDETRBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 0.5876 | |
| MV-D-MDETRBackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 0.5473 | |
| MV-MMCABackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 0.5362 | |
| MV-TransVGBackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 0.5318 | |
| MV-CLIP-VGBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 0.4702 |