List your company
ResearchFormerly WizWand

Visual Grounding on RefFLIR 1.0 (val)

73.68Accuracy @ 0.5 IoURGBT-VGNet
2.013620.619339.22557.8307Dec 31, 2025
Updated 8mo ago

Evaluation results

MethodLinks
RGBT-VGNetVisual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=RGB+TIR, Evaluation Setting=Baseline2025.1273.68
HiVG-BVenue=ACMMM’24, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1269.08
HiVG-LVenue=ACMMM’24, Visual / Language Backbone=CLIP-L / CLIP-L, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1268.75
HiVG-BVenue=ACMMM’24, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1268.75
OneRef-LVenue=NeurIPS’24, Visual / Language Backbone=BEIT3-L / BEIT3-L, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1266.61
HiVG-LVenue=ACMMM’24, Visual / Language Backbone=CLIP-L / CLIP-L, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1265.79
OneRef-LVenue=NeurIPS’24, Visual / Language Backbone=BEIT3-L / BEIT3-L, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1264.14
OneRef-BVenue=NeurIPS’24, Visual / Language Backbone=BEIT3-B / BEIT3-B, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1263.82
OneRef-BVenue=NeurIPS’24, Visual / Language Backbone=BEIT3-B / BEIT3-B, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1262.01
D-MDETRVenue=TPAMI’24, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1257.07
TransVGVenue=ICCV’21, Visual / Language Backbone=RN50+DETR / BERT-B, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1250.74
D-MDETRVenue=TPAMI’24, Visual / Language Backbone=RN50+DETR / BERT-B, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1250.57
MMCAVenue=ACMMM’24, Visual / Language Backbone=RN50+DETR / BERT-B, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1250.16
TransVGVenue=ICCV’21, Visual / Language Backbone=RN50+DETR / BERT-B, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1249.92
D-MDETRVenue=TPAMI’24, Visual / Language Backbone=RN50+DETR / BERT-B, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1249.67
MMCAVenue=ACMMM’24, Visual / Language Backbone=RN50+DETR / BERT-B, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1248.52
D-MDETRVenue=TPAMI’24, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1248.36
CLIP-VGVenue=TMM’23, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.1243.68
OneRef-LVenue=NeurIPS’24, Visual / Language Backbone=BEIT3-L / BEIT3-L, Visual Modality=RGB, Evaluation Setting=Pretrained model zero-shot transfer2025.1238.82
CLIP-VGVenue=TMM’23, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.1236.59
HiVG-LVenue=ACMMM’24, Visual / Language Backbone=CLIP-L / CLIP-L, Visual Modality=RGB, Evaluation Setting=Pretrained model zero-shot transfer2025.1234.05
OneRef-BVenue=NeurIPS’24, Visual / Language Backbone=BEIT3-B / BEIT3-B, Visual Modality=RGB, Evaluation Setting=Pretrained model zero-shot transfer2025.1232.89
HiVG-BVenue=ACMMM’24, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=RGB, Evaluation Setting=Pretrained model zero-shot transfer2025.1223.03
OneRef-LVenue=NeurIPS’24, Visual / Language Backbone=BEIT3-L / BEIT3-L, Visual Modality=TIR, Evaluation Setting=Pretrained model zero-shot transfer2025.1221.55
OneRef-BVenue=NeurIPS’24, Visual / Language Backbone=BEIT3-B / BEIT3-B, Visual Modality=TIR, Evaluation Setting=Pretrained model zero-shot transfer2025.1221.38
HiVG-LVenue=ACMMM’24, Visual / Language Backbone=CLIP-L / CLIP-L, Visual Modality=TIR, Evaluation Setting=Pretrained model zero-shot transfer2025.1218.26
HiVG-BVenue=ACMMM’24, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=TIR, Evaluation Setting=Pretrained model zero-shot transfer2025.1210.86
CLIP-VGVenue=TMM’23, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=RGB, Evaluation Setting=Pretrained model zero-shot transfer2025.125.59
CLIP-VGVenue=TMM’23, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=TIR, Evaluation Setting=Pretrained model zero-shot transfer2025.124.77