| Full name | Vote2Cap-DETR++ |
| Description | Decoupled feature extraction and task decoding for 3D dense captioning.
Set-to-set training, and fine-tuned with SCST (CiDEr reward) |
| Publication title | Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning |
| Publication authors | Sijin Chen, Hongyuan Zhu, Mingsheng Li, Xin Chen, Peng Guo, Yinjie Lei, Gang Yu, Taihao Li, Tao Chen |
| Publication URL | https://arxiv.org/abs/2309.02999 |
| Input Data Types | Uses XYZ coordinates,Uses RGB values,Uses Normal Vectors |
| Programming language(s) | python |
| Hardware | RTX3090 |
| Source code or download URL | https://github.com/ch3cook-fdu/Vote2Cap-DETR |
| Submission creation date | 16 Feb, 2024 |
| Last edited | 19 Feb, 2024 |