| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| 3D Dense Captioning | ReferIt3D Nr3D (test) | C Score (0.5 IoU)45.53 | 13 | |
| Referring Expression Segmentation | ReferIt3D Nr3D | mIoU32.4 | 7 | |
| Object Detection | ReferIt3D Nr3D (test) | mAP@0.50.5269 | 5 | |
| 3D Visual Grounding | ReferIt3D Nr3D (val) | Accuracy@0.5IoU (Multiple)25.23 | 5 | |
| 3D Dense Captioning | ReferIt3D Nr3D (val) | C Score @0.5IoU33.71 | 5 | |
| Referring Expression Segmentation | ReferIt3D Sr3D | mIoU34.9 | 3 |