Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision
Sign Up to like & getrecommendations! Published in 2022 at "International Journal of Computer Vision"
DOI: 10.1007/s11263-021-01547-8
Abstract: Transformer architectures have brought about fundamental changes to computational linguistic field, which had been dominated by recurrent neural networks for many years. Its success also implies drastic changes in cross-modal tasks with language and vision,… read more here.
Keywords: tasks language; transformer architecture; language vision; cross modal ... See more keywords