論文サマリ

emnlp2019
tag: vision-and-language

LXMERT: Learning Cross-Modality Encoder Representations from Transformers
by: Yuta Nakamura
vision-and-language BERT transformer VQA GQA BUTD
Incorporating Visual Semantics into Sentence Representations within a Grounded Space
by: Shintaro Yamamoto
Language Grounding Visual Semantics Vision and Language