@misc{parelli2023clip,
  title={CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes},
  author={Maria Parelli and Alexandros Delitzas and Nikolas Hars and Georgios Vlassis and Sotirios Anagnostidis and Gregor Bachmann and Thomas Hofmann},
  year={2023},
  eprint={2304.06061},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2304.06061}
}