Results for CM3D-Trans+
Submission data
| Full name | GroupFree 3D+Multi-Transformer |
| Publication title | Contextual Modeling for 3D Dense Captioning on Point Clouds |
| Publication authors | Yufeng Zhong, Long Xu, Jiebo Luo, Lin Ma |
| Publication URL | https://arxiv.org/abs/2210.03925 |
| Input Data Types | Uses XYZ coordinates,Uses Multiview Image Features,Uses Normal Vectors |
| Programming language(s) | Python |
| Hardware | RTX 3090Ti |
| Submission creation date | 27 Sep, 2022 |
| Last edited | 13 Oct, 2022 |
Captioning
| Captioning F1-Score | Dense Captioning | Object Detection | |||
|---|---|---|---|---|---|
| CIDEr@0.5IoU | BLEU-4@0.5IoU | Rouge-L@0.5IoU | METEOR@0.5IoU | DCmAP | mAP@0.5 |
| 0.2348 | 0.1383 | 0.2250 | 0.1030 | 0.1398 | 0.2966 |