Visual Grounding on RefMFAD 1.0 (testC)
49.76Acc@0.5RGBT-VGNet
Evaluation results
| Method | Links | |
|---|---|---|
| RGBT-VGNetVisual Modality=RGB+TIR, Evaluation Setting=Baseline2025.12 | 49.76 | |
| HiVG-BVenue=ACMMM’24, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=TIR, Evaluation Setting=Single source dataset training2025.12 | 45.69 | |
| D-MDETRVenue=TPAMI’24, Visual / Language Backbone=CLIP-B / CLIP-B, Visual Modality=RGB, Evaluation Setting=Single source dataset training2025.12 | 40.98 |