Bio
Jan is a research scientist at CyberAgent, where he works on artificial intelligence and computer vision
with a focus on image generation and editing. He received his PhD in Information Science and Technology
from the University of Tokyo, where his research centered on image generation. Prior to that, he received
his Master’s degree in Creative Informatics from the University of Tokyo, and his Bachelor’s degree
in Computer and Information Science from the Czech Technical University in Prague.
Born and raised in the Czech Republic, he currently works in Japan.
Education
PhD in Information Science and Technology
2017-10-01
2022-09-30
University of Tokyo
MS in Information Science and Technology
2015-09-23
2017-09-30
University of Tokyo
BE in Information and Computer Science
2011-09-01
2014-06-30
Czech Technical University in Prague
Interests
Artifical Intelligence
Computer Vision
Machine Learning
Image Generation
Experience
Research Scientist
CyberAgent
Conducting research on image generation and editing tasks.
Research Assistant
The University of Tokyo, Graduate School of Information Science and Technology
Participated in Beyond AI, a joint research program of The University of Tokyo and Softbank.
Research on image generation of handwritten text and text in natural scene images.
Machine Learning Engineer Intern
RESTAR
Participated in development of an OCR system for automatic conversion of real estate data documents
from PDF to machine-readable form for an automatic generation of database of real estate data.
Research Intern
Center for Machine Perception
Participated in research on scene text detection and recognition.
Education
PhD in Information Science and Technology
University of Tokyo
Research on image generation and editing.
Thesis on generation and editing of handwritten text.
MS in Information Science and Technology
University of Tokyo
BE in Information and Computer Science
Czech Technical University in Prague
Publications (w/ peer review)
(2025).
OTR: Synthesizing Overlay Text Dataset for Text Removal.
ACMMM 2025.
(2025).
Controllable Font Style for Visual Text Generation Using Reference Images.
ICONIP 2025.
(2023).
Handwritten Text Generation with Character-specific Encoding for Style Imitation.
ICDAR 2023.
(2022).
Meta Approach to Data Augmentation Optimization.
WACV 2022.
Other papers
Papers w/o peer review (e.g. domestic conference presentations)
(2025).
OTR: Synthesizing Overlay Text Dataset for Text Removal.
MIRU 2025.
(2024).
Erasing Scene Text with Foundation Models.
MIRU 2024.
(2024).
グラフィックデザイン再編集のためのテキスト分離に向けて (Towards Text Decomposition for Graphic Design Re-editing).
MIRU 2024.
(2023).
Can We Erase Japanese Text from Images Without Japanese Training Data?.
MIRU 2023.
(2021).
Efficient Model for Handwritten Text Generation with Text Line Awareness.
MIRU 2021.
Competitions
Awards
Outstanding Reviewer CVPR 2025
IEEE/CVF Conference on Computer Vision and Pattern Recognition ∙
June 2025
Outstanding Reviewer Award at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025.
MIRU 2020 Student Paper Award
Meeting on Image Recognition and Understanding ∙
August 2020
Best Student Paper Award at the Meeting on Image Recognition and Understanding (MIRU) 2020 for the paper by Hataya R.,
Zdenek J., Yoshizoe K., Nakayama H., titled “MADAO: データ拡張最適化のためのメタ的アプローチ (English title: Meta Approach
to Data Augmentation Optimization)”.
Student Incentive Award 2017
The Japanese Society for Artificial Intelligence (JSAI) Annual Conference ∙
July 2017
Student Incentive Award at the Japanese Society for Artificial Intelligence (JSAI) Annual Conference 2017
for the paper titled “Script Identification using Bag-of-Words with Entropy-weighted Patches”
Japanese Government (MEXT) Scholarship for Research Students
Ministry of Education, Culture, Sports, Science and Technology (Government of Japan) ∙
April 2015
I was selected as a recipient of the Japanese Government (Monbukagakusho - MEXT) Scholarship for Research Students
from 2015 to 2017 for the duration of my Master’s program at the University of Tokyo.
Later, I received a recommendation by the university for an extension of my scholarship for my PhD course until 2020.
Dean’s Award for an Outstanding Bachelor Thesis
Czech Technical University in Prague ∙
June 2014
Dean’s Award for an Outstanding Bachelor Thesis at the Czech Technical University in Prague for the bachelor thesis
titled “Mobile Application for Recognition of Japanese Writing System”
Other activities
Teaching assistant
I have worked as a teaching assistant for Data Science course at the University of Tokyo, Graduate School of Information Science and Technology.
Peer review
I have served as a reviewer for academic conferences such as CVPR, ECCV, ICCV, ICLR, AAAI, SIGGRAPH, and journals such as TIP.
Languages
100%
Czech
Native
100%
English
Fluent
90%
Japanese
Fluent