Assistant Prof. Seitaro Shinagawa (Augmented Human Communication Laboratory)
TITLE: Recent Advancements of Transformers in Vision and Language Fields
Transformers have become the new standard model architecture in many research fields. I would like to summarize recent advancements of transformers in Computer Vision and Natural Language Processing to handle them more reasonably. I also plan to introduce recent useful applications using transformer-based Vision and Language models and discuss their remaining problems and what I am working on.