@misc{multimodalityvilt2021,
  title = {{ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision}},
  author = {Wonjae Kim and Bokyung Son and Ildoo Kim},
  year = {2021},
  eprint = {2102.03334},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2102.03334}
}
