@article{mtfnetmutualtransformerfusionnetworkfor,
  title = {MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention},
  author = {Xixi Wang and Xiao Wang and Bo Jiang and Jin Tang and Bin Luo},
  year = {2021},
  eprint = {2112.01177},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.01177v3},
}