Visual Grounding on RefMFAD RGBT-Ground (test)
67.04Accuracy @ 0.5 IoUMV-HiVG-B
Evaluation results
| Method | Links | |
|---|---|---|
| MV-HiVG-BBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 67.04 | |
| RGBT-VGNetBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 66.63 | |
| MV-OneRef-LBackbone=BEIT3-L / BEIT3-L, Modality=RGB+TIR2025.12 | 62.73 | |
| MV-HiVG-LBackbone=CLIP-L / CLIP-L, Modality=RGB+TIR2025.12 | 61.31 | |
| MV-OneRef-BBackbone=BEIT3-B / BEIT3-B, Modality=RGB+TIR2025.12 | 59.97 | |
| MV-D-MDETRBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 57.31 | |
| MV-MMCABackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 54.41 | |
| MV-D-MDETRBackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 54.13 | |
| MV-TransVGBackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 53.84 | |
| MV-CLIP-VGBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 47.52 |