@article{Shin2022Perspectives,
author = {Andrew Shin and
Masato Ishii and
Takuya Narihira},
title = {Perspectives and Prospects on Transformer Architecture for Cross-Modal
Tasks with Language and Vision},
journal = {Int. J. Comput. Vis.},
volume = {130},
number = {2},
pages = {435--454},
year = {2022},
url = {https://doi.org/10.1007/s11263-021-01547-8},
doi = {10.1007/s11263-021-01547-8},
timestamp = {Tue, 15 Mar 2022 10:21:36 +0100},
biburl = {https://dblp.org/rec/journals/ijcv/ShinIN22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}