List your company

Visual Grounding on RefM3FD RGBT-Ground (test)

74.34Accuracy @ 0.5RGBT-VGNet
37.503247.066656.6366.1934Dec 31, 2025

Evaluation results

MethodLinks
RGBT-VGNetBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.1274.34
MV-HiVG-BBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.1272.35
MV-OneRef-LBackbone=BEIT3-L / BEIT3-L, Modality=RGB+TIR2025.1269.7
MV-HiVG-LBackbone=CLIP-L / CLIP-L, Modality=RGB+TIR2025.1268.67
MV-OneRef-BBackbone=BEIT3-B / BEIT3-B, Modality=RGB+TIR2025.1263.98
MV-TransVGBackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.1248.04
MV-MMCABackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.1247.83
MV-D-MDETRBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.1246.5
MV-D-MDETRBackbone=RN50+DETR / BERT-B, Modality=RGB+TIR2025.1245.62
MV-CLIP-VGBackbone=CLIP-B / CLIP-B, Modality=RGB+TIR2025.1238.92