| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| 3D Visual Grounding | Sr3D (test) | Overall Accuracy81.7 | 73 | |
| 3D Visual Grounding | Sr3D | Overall Accuracy77.8 | 15 | |
| 3D Referring Expression Segmentation | SR3D | Acc@0.2570.95 | 11 | |
| 3D referring expression comprehension | SR3D ReferIt3D (test) | Overall Accuracy67 | 11 | |
| Scene Retrieval | Sr3D (n=10) | R@14.6 | 8 | |
| Scene Retrieval | Sr3D n=5 | R@13 | 8 | |
| Viewpoint Grounding | Sr3D | Recall@123.6 | 6 | |
| Text-based Object Retrieval | Sr3D | Acc@0.126 | 5 | |
| 3D Referring Expression Comprehension | SR3D | Accuracy @ IoU=0.2570.95 | 2 |