Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs

Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs Emanuele Bugliarello author Ryan Cotterell author Naoaki Okazaki author Desmond Elliott author 2021 text journal article Transactions of the Association for Computational Linguistics continuing MIT Press Cambridge, MA periodical academic journal bugliarello-etal-2021-multimodal 10.1162/tacl_a_00408 https://aclanthology.org/2021.tacl-1.58/ 2021 9 978 994