| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sun, 16 Feb 2025 07:03:20 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"67b18db8-2b27"
expires: Sun, 28 Dec 2025 23:28:14 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 6D4F:328FD3:81561A:9130B7:6951BAB4
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 23:18:14 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210036-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766963894.940285,VS0,VE231
vary: Accept-Encoding
x-fastly-request-id: cc9a9f1f00790237f89b7fe1f7c24d965d91bd1d
content-length: 3197
Koki Tsubota
E-mail: tsubota (at) hal.t.u-tokyo.ac.jp
Koki Tsubota
Machine Learning Engineer (Apr. 2023 - present)E-mail: tsubota (at) hal.t.u-tokyo.ac.jp
Research Interests
Computer Vision, Image Compression, Manga.Education
- Ph.D., (Apr. 2020 - Mar. 2023)
- Department of Information and Communication Engineering,
- Graduate School of Information Science and Technology,
The University of Tokyo.
Advisor: Prof. Kiyoharu Aizawa
- Graduate School of Information Science and Technology,
- M.S., (Apr. 2018 - Mar. 2020)
- Department of Information and Communication Engineering,
- Graduate School of Information Science and Technology,
The University of Tokyo.
Advisor: Prof. Kiyoharu Aizawa - Graduate School of Information Science and Technology,
- B.E., (Apr. 2014 - Mar. 2018)
- Department of Information and Communication Engineering,
The University of Tokyo.
Advisor: Prof. Kiyoharu Aizawa and Prof. Toshihiko Yamasaki
Publications
Journals
- Koki Tsubota, and Kiyoharu Aizawa
Content-Adaptive Optimization Framework for Universal Deep Image Compression
IEICE Transactions on Information and Systems, vol. E107.D, Issue 2, pp. 201-211, 2024. [pdf] - Takahiro Naruko, Hiroaki Akutsu, Koki Tsubota, and Kiyoharu Aizawa
Quality Enhancement of Conventional Compression with a Learned Side Bitstream
IEICE Transactions on Information and Systems (Letter), vol. E106.D, Issue 8, pp. 1296-1299, 2023. [pdf] - Koki Tsubota, and Kiyoharu Aizawa
Comprehensive Comparisons of Uniform Quantization in Deep Image Compression
IEEE Access, vol. 11, pp. 4455-4465, 2023. [pdf] [arXiv] [code] - Koki Tsubota, Hiroaki Akutsu, and Kiyoharu Aizawa
Evaluating the Stability of Deep Image Quality Assessment with Respect to Image Scaling
IEICE Transactions on Information and Systems (Letter), vol. E105.D, Issue 10, pp. 1829-1833, 2022. [pdf] [arXiv] - Kiyoharu Aizawa, Azuma Fujimoto, Atsushi Otsubo, Toru Ogawa, Yusuke Matsui, Koki Tsubota, and Hikaru Ikuta
Building a Manga Dataset "Manga109" with Annotations for Multimedia Applications
IEEE MultiMedia, vol. 27, no. 2, pp. 8-18, 2020. [pdf]
International conferences
- Jihun Kang, Daichi Horita, Koki Tsubota, and Kiyoharu Aizawa
Restorable Visible and Infrared Image Fusion
ICIP, pp. 1560-1564, Kuala Lumpur, 2023. [pdf] - Koki Tsubota, Hiroaki Akutsu, and Kiyoharu Aizawa
Universal Deep Image Compression via Content-Adaptive Optimization with Adapters
WACV, pp. 2529-2538, Hawaii, 2023. [pdf] [arXiv] [code] - Koki Tsubota and Kiyoharu Aizawa
Comprehensive Comparisons of Uniform Quantizers for Deep Image Compression
ICIP, pp. 2089-2093, Anchorage (Virtual), 2021. [pdf] [code] - Keita Awane, Koki Tsubota, Hikaru Ikuta, Yusuke Matsui, Kiyoharu Aizawa, and Naohiro Yanase
Improving the Quality of Illustrations: Transforming Amateur Illustrations to a Professional Standard
ICIP, pp. 584-588, Anchorage (Virtual), 2021. [pdf] - Akifumi Suzuki, Hiroaki Akutsu, Takahiro Naruko, Koki Tsubota, and Kiyoharu Aizawa
Learned Image Compression With Super-Resolution Residual Modules and DISTS Optimization
CVPRW, pp. 1906-1910, Virtual, 2021. [pdf] - Haruka Aoki, Koki Tsubota, Hikaru Ikuta, and Kiyoharu Aizawa
Few-Shot Font Generation with Deep Metric Learning
ICPR, pp. 8539-8546, Milano (Virtual), 2020. [pdf] [arXiv] - Koki Tsubota and Kiyoharu Aizawa
Unsupervised Embedding Learning by Noisy Similarity Label Optimization
VCIP (oral), pp. 247-250, Macau (Virtual), 2020. [pdf] - Koki Tsubota, Daiki Ikami, and Kiyoharu Aizawa
Synthesis of Screentone Patterns of Manga Characters
IEEE ISM (short), pp. 212-215, San Diego, 2019. [pdf] [code] - Koki Tsubota, Toru Ogawa, Toshihiko Yamasaki, and Kiyoharu Aizawa
Adaptation of Manga Face Representation for Accurate Clustering
SIGGRAPH Asia (poster), pp. 15:1-15:2, Tokyo, 2018. [pdf] [code] - Rei Narita, Koki Tsubota, Toshihiko Yamasaki, and Kiyoharu Aizawa
Sketch-Based Manga Retrieval Using Deep Features
ICDAR Workshop on MANPU, pp. 49-53, Kyoto, 2017. [pdf]
Awards
- FY2022 IE Special Award (Best Award), Technical Committee on Image Engineering, Institute of Electronics, Information and Communication Engineers, 2023.
Invited Talks
- FY2022 IE Special Award Memorial Talk: A Study on Adaptation Methods for Universal Deep Image Compression, PCSJ/IMPS, 2023.
Others
- Jinjin Gu, et al.,
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
CVPRW, 14 pages, 2021. [pdf] [arXiv]
Domestic conferences
- 26 papers
Misc
- Research fellowship for young scientists (DC2), Japan Society for the Promotion of Science (JSPS) (Apr. 2022 - Mar. 2023) [grant (Japanese)]
- Doctoral Student Special Incentives Program (IST-RA) (Apr. 2020 - Mar. 2022)
- Kaggle Expert
- Internship at Yahoo Japan Corporation (Aug. 2018, two weeks)
- Part-time job at priceless, Inc. (Apr. 2017 - Aug. 2018) and pluszero, Inc. (Sep. 2018 - Mar. 2022)
Links
- Aizawa Yamakata Matsui Laboratory
- Graduate School of Information Science and Technology
- The University of Tokyo
- pluszero