@article{bugliarello-etal-2021-multimodal,
    title = "Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language {BERT}s",
    author = "Bugliarello, Emanuele  and
      Cotterell, Ryan  and
      Okazaki, Naoaki  and
      Elliott, Desmond",
    editor = "Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "9",
    year = "2021",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.tacl-1.58/",
    doi = "10.1162/tacl_a_00408",
    pages = "978--994"
}