@misc{xu2022multimodal,
  title={Multimodal Learning with Transformers: A Survey},
  author={Peng Xu and Xiatian Zhu and David A. Clifton},
  year={2022},
  eprint={2206.06488},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2206.06488}
}