Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision
This is an incremental review paper that synthesizes existing research for researchers in computational linguistics and vision.
The paper reviews the impact of transformer architectures on cross-modal tasks involving language and vision, highlighting key milestones and trends, and discusses current limitations and future prospects.
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, and many researchers have already tackled the issue. In this paper, we review some of the most critical milestones in the field, as well as overall trends on how transformer architecture has been incorporated into visuolinguistic cross-modal tasks. Furthermore, we discuss its current limitations and speculate upon some of the prospects that we find imminent.