@article{perspectivesandprospectsontransformer,
  title = {Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision},
  author = {Andrew Shin and Masato Ishii and Takuya Narihira},
  year = {2021},
  eprint = {2103.04037},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2103.04037v2},
}