Open-world driving scene segmentation via multi-stage and multi-modality fusion of vision-language embedding

Yingjie Niu, Ming Ding, Yuxiao Zhang, Maoning Ge, Hanting Yang, Kazuya Takeda. Open-world driving scene segmentation via multi-stage and multi-modality fusion of vision-language embedding. In IEEE Intelligent Vehicles Symposium, IV 2023, Anchorage, AK, USA, June 4-7, 2023. pages 1-6, IEEE, 2023. [doi]

@inproceedings{NiuDZGYT23,
  title = {Open-world driving scene segmentation via multi-stage and multi-modality fusion of vision-language embedding},
  author = {Yingjie Niu and Ming Ding and Yuxiao Zhang and Maoning Ge and Hanting Yang and Kazuya Takeda},
  year = {2023},
  doi = {10.1109/IV55152.2023.10186652},
  url = {https://doi.org/10.1109/IV55152.2023.10186652},
  researchr = {https://researchr.org/publication/NiuDZGYT23},
  cites = {0},
  citedby = {0},
  pages = {1-6},
  booktitle = {IEEE Intelligent Vehicles Symposium, IV 2023, Anchorage, AK, USA, June 4-7, 2023},
  publisher = {IEEE},
  isbn = {979-8-3503-4691-6},
}