@misc{zeng2023clip,
  title={CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data},
  author={Yihan Zeng and Chenhan Jiang and Jiageng Mao and Jianhua Han and Chaoqiang Ye and Qingqiu Huang and Dit-Yan Yeung and Zhen Yang and Xiaodan Liang and Hang Xu},
  year={2023},
  eprint={2303.12417},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2303.12417}
}