Emanuele Bugliarello, Ryan Cotterell, Naoaki Okazaki, Desmond Elliott. Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs. TACL, 9:978-994, 2021. [doi]
@article{BugliarelloCOE21,
title = {Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs},
author = {Emanuele Bugliarello and Ryan Cotterell and Naoaki Okazaki and Desmond Elliott},
year = {2021},
doi = {10.1162/tacl_a_00408},
url = {https://doi.org/10.1162/tacl_a_00408},
researchr = {https://researchr.org/publication/BugliarelloCOE21},
cites = {0},
citedby = {0},
journal = {TACL},
volume = {9},
pages = {978-994},
}