I am working at Aizawa-Yamakata-Matsui Lab, as a Ph.D. candidate. My research interests are in the interdisciplinary field between computer vision and natural language processing, especially in anything related to text recognition, including TextVQA, TextCaps, and synthetic data generation. I have developed the scene text recognition model.
CV | email | Google Scholar | LinkedIn | Github
Google Research, Oct. 2022 - Jan. 2023
As a student researcher, I worked in the Google OCR team, from the Google Japan office or home.
Clova AI Research, NAVER Corp., Korea, Jan. 2018 - Mar. 2020
Developed scene text recognition (STR) model, which recognizes text in the natural scene.
Language Analytics, NCSOFT Corp., Korea, Apr. 2016 - Dec. 2017
Developed sentence embedding model for question/document clustering and text style transfer model for colloquial text generation.
The University of Tokyo, Apr. 2020 - Present (Expected to graduate in Mar. 2023)
Kyoto University, Apr. 2014 - Mar. 2016