Biography
I am Shumpei Takezaki (竹崎 隼平 in Japanse), a Ph.D student at Kyushu University, Fukuoka, JAPAN, under the supervision of Prof. Seiichi Uhicda.
Before starting my Ph.D, I received my undergraduate degree in ECE from the Kagoshima Technical College, Kagoshima, JAPAN.
My research is on generative modeling. I am particularly interested in the applications of generative modeling for medical imaging.
News
- [Paper Acceptance]: NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models got accepted to ICCV 2025 Workshop.
- [Paper Acceptance]: Few-Part-Shot Font Generation got accepted to ICDAR 2025 Workshop.
- [Paper Acceptance]: Inverse Scene Text Removal got accepted to ICDAR 2025.
Publications
For a more comprehensive list of publications, please see Publications or visit Google Scholar page.
NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models
Published in ICCV 2025 Workshop [Paper] [Code]
Citation: Shumpei Takezaki, Ryoma Bise, Shinnosuke Matsuo, "NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models", ICCV 2025 Workshop
Few-Part-Shot Font Generation
Published in ICDAR 2025 Workshop
Citation: Masaki Akiba, Shumpei Takezaki, Daichi Haraguchi, Seiichi Uchida, "Few-Part-Shot Font Generation", ICDAR 2025 Workshop
Inverse Scene Text Removal
Published in ICDAR 2025 [Paper] [Code]
Citation: Takumi Yoshimatsu, Shumpei Takezaki, Seiichi Uchida, "Inverse Scene Text Removal", ICDAR 2025
Contact
- Address: Human Interface Laboratory, Department of Advanced Information Technology, Kyushu University. 744, Motooka, Nishi-ku, Fukuoka-shi, 819-0395 JAPAN
- TEL: +81-92-802-3574
- E-mail: shumpei.takezaki[at]human.ait.kyushu-u.ac.jp