Visual Grounding on RefFLIR RGBT-Ground (val)
0.7533Acc@0.5MV-HiVG-B
Evaluation Results
| Method | Links | |
|---|---|---|
| MV-HiVG-BBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 0.7533 | |
| RGBT-VGNetBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 0.7368 | |
| MV-HiVG-LBackbone=CLIP-L / CLIP-L, Modality=RGB+TIR2025.12 | 0.7105 | |
| MV-OneRef-LBackbone=BEIT3-L / BEIT3-L, Modality=RGB+TIR2025.12 | 0.6661 | |
| MV-OneRef-BBackbone=BEIT3-B / BEIT3-B, Modality=RGB+TIR2025.12 | 0.6382 | |
| MV-D-MDETRBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 0.5526 | |
| MV-D-MDETRBackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 0.5501 | |
| MV-MMCABackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 0.5493 | |
| MV-TransVGBackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.12 | 0.5444 | |
| MV-CLIP-VGBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.12 | 0.4557 |