Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Koki Tsubota"'
Autor:
Koki Tsubota, Kiyoharu Aizawa
Publikováno v:
IEEE Access, Vol 11, Pp 4455-4465 (2023)
In deep image compression, uniform quantization is applied to latent representations obtained by using an auto-encoder architecture for reducing bits and entropy coding. Quantization is a problem encountered in the end-to-end training of deep image c
Externí odkaz:
https://doaj.org/article/306b87a84ac546bab190fdc9f5ff4925
Autor:
Koki Tsubota, Kiyoharu Aizawa
Publikováno v:
2021 IEEE International Conference on Image Processing (ICIP).
Publikováno v:
2021 IEEE International Conference on Image Processing (ICIP).
Autor:
Wassim Hamidouche, Byungyeon Kang, Shuwei Shi, Yujiu Yang, Junlin Li, Pengfei Sun, Jose Costa Pereira, Kele Xu, Hiroaki Akutsu, Hai Wang, Koki Tsubota, Yiting Liao, William Thong, Hengliang Luo, Longtao Feng, Jingyu Guo, Yuqing Hou, Yu Qiao, Sung-Jun Yoon, Jimmy Ren, Tao Zhang, Yang Li, Bin Yi, Yifan Chen, Jinjin Gu, Ali Royat, Steven McDonagh, Shuhang Gu, Junwoo Lee, Kiyoharu Aizawa, Lehan Yang, Sewoong Ahn, Weihao Xia, Qingyan Bai, Haiyang Guo, Zirui Wang, Mingdeng Cao, Qing Zhang, Jiahao Wang, Wenming Yang, Sid Ahmed Fezza, Haoming Cai, Dounia Hammou, Ales Leonardis, Radu Timofte, Hengxing Cai, Manri Cheon, Seyed Mehdi Ayyoubzadeh, Chao Dong, Gwangjin Yoon
Publikováno v:
CVPR Workshops
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a new type of image processing techno
Publikováno v:
CVPR Workshops
Neural network-based image compressors have the ability to optimize various perceptual image quality metrics. We propose improved methods that is based on selective-detail decoding, which uses two decoders (a main decoder and selective-detail decoder
Publikováno v:
ICPR
Designing fonts for languages with a large number of characters, such as Japanese and Chinese, is an extremely labor-intensive and time-consuming task. In this study, we addressed the problem of automatically generating Japanese typographic fonts fro
Autor:
Kiyoharu Aizawa, Koki Tsubota
Publikováno v:
VCIP
We propose a similarity label optimization framework for unsupervised embedding learning. Existing works use similarity labels obtained from instance labels, which are image identifiers, for unsupervised embedding learning assuming that images of dif
Autor:
Toru Ogawa, Koki Tsubota, Atsushi Otsubo, Azuma Fujimoto, Yusuke Matsui, Hikaru Ikuta, Kiyoharu Aizawa
Manga, or comics, which are a type of multimodal artwork, have been left behind in the recent trend of deep learning applications because of the lack of a proper dataset. Hence, we built Manga109, a dataset consisting of a variety of 109 Japanese com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::310648b5f5dab3bca8257252ba1143b0
Publikováno v:
ISM
Manga or Japanese comics are a popular medium and their images comprise line drawings and screentones. This study investigates the screentone synthesis task that involves translation from line drawings to manga images. Screentones have regular patter
Publikováno v:
SIGGRAPH ASIA Posters
Manga character drawing styles differ greatly among artists. To accurately cluster faces within an individual manga, we propose a method to adapt manga face representations to an individual manga. We use deep features trained for generic manga face r