About Me
FUJITAKE Masato (藤武将人) is a Co-Founder of Fast Accounting, Ltd., Tokyo, Japan, and Research Director of its Research dept, FA Research. His technical interests include computer vision, and machine learning, especially document analysis recently.
He received his Ph.D. degree in information science and technology. He was a Computer Vision and Discrete Geometry Group (Sugimoto Laboratory) member at the National Institute of Informatics (NII), Japan. Before commencing his graduate studies at the Graduate University for Advanced Studies, SOKENDAI, he earned his bachelor and master’s degree in robotics and information science at the Shibaura Institute of Technology in Tokyo, Japan, where he was born and grew up.
He is enthusiastic about contributing to open-source projects, such as a model analyzer called torchstat and a detection error analyzer named Nobunaga. He is a member of IEEE and The Association for Natural Language Processing. He is also a reviewer of IEEE conferences.
Research Interests
- Computer Vision
- Machine Learning
- Document Analysis
- Video Analysis
News (Past year)
- 2024/04: We introduced our paper “RL-LOGO: Deep Reinforcement Learning Localization for Logo Recognition” in ICASSP2024.
- 2024/03: Our paper “LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding” has been accepted to LREC-COLING2024. It is available on arXiv
- 2024/01: Our paper “RL-LOGO: Deep Reinforcement Learning Localization for Logo Recognition” has been accepted to ICASSP2024.
- 2024/01: We present our paper “DTrOCR: Decoder-only Transformer for Optical Character Recognition” in WACV 2024. See you soon.
- 2023/12: Our paper “FA Team at the NTCIR-17 UFO Task” has been available at the 17th NTCIR 17 Conference.
- 2023/11: Our paper “FA Team at the NTCIR-17 UFO Task” has been available at arXiv.
- 2023/10: We present our paper “DiffusionSTR: Diffusion Model for Scene Text Recognition” in IEEE ICIP2023. See you soon.
- 2023/09: Our paper “DiffusionSTR: Diffusion Model for Scene Text Recognition” has been available on IEEE!
- 2023/09: Our paper “DTrOCR: Decoder-only Transformer for Optical Character Recognition” has been accepted in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024! arXiv
- 2023/07: I’ll present “拡散モデルを用いたシーンテキスト認識” in Poster IS2-88 at MIRU 2023!
- 2023/06: Our paper “DiffusionSTR: Diffusion Model for Scene Text Recognition” has been accepted in IEEE ICIP 2023! arXiv
- 2023/06: Our paper “A3S: ADVERSARIAL LEARNING OF SEMANTIC REPRESENTATIONS FOR SCENE-TEXT SPOTTING” has been recognized as one of the top 3% of all papers accepted at ICASSP 2023!
- 2023/05: Our paper “A3S: ADVERSARIAL LEARNING OF SEMANTIC REPRESENTATIONS FOR SCENE-TEXT SPOTTING” has been available on IEEE!
Educations
- PhD in Information Science and Technology, 2022
- The Graduate University for Advanced Studies, SOKENDAI
- Master of Electrical, Electronic and Communications Engineering, 2019
- Shibaura Institute of Technology, Tokyo
- Bachelor of Electrical Engineering Technologies, 2017
- Shibaura Institute of Technology, Tokyo
Work Experience
- Research Engineer, 2016/11 ~ 2022/03, Fast Accounting, Japan
- Research Assistant, 2020/04 ~ 2022/02, National Institute of Informatics, Japan
- Research Scientist, 2022/04 ~ 2023/02, Fast Accounting, Japan
- Chief Research Scientist, 2023/02 ~ 2024/01, Fast Accounting, Japan
- Research Director, 2024/01 ~ present, Fast Accounting, Japan