Toshihiko Yamasaki - My portal

Profile Information

Affiliation: Professor, Department of Information and Communication Engineering, The Graduate School of Information Science and Technology , The University of Tokyo

Degree: 博士(工学)(東京大学)

J-GLOBAL ID: 201101054011904547
researchmap Member ID: B000000859

External link: http://www.cvm.t.u-tokyo.ac.jp/

Research Interests

Research Areas

Research History

Sep, 2022

Professor, Department of Information and Communication Engineering, The Graduate School of Information Science and Technology, The University of Tokyo
Apr, 2009 - Aug, 2022

The Graduate School of Information Science and Technology, Department of Information and Communication Engineering, The University of Tokyo
Feb, 2011 - Feb, 2013

日本学術振興会海外特別研究員
Oct, 2006 - Mar, 2009

The Graduate School of Information Science and Technology, Department of Information and Communication Engineering, The University of Tokyo
Apr, 2004 - Oct, 2006

Graduate School of Frontier Sciences, Department of Frontier Intormatics, The University of Tokyo

Papers

241

Cross-Lingual Learning in Multilingual Scene Text Recognition.

Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa

CoRR, abs/2312.10806, 2023
Manga109Dialog A Large-scale Dialogue Dataset for Comics Speaker Detection.

Yingxuan Li, Kiyoharu Aizawa, Yusuke Matsui

CoRR, abs/2306.17469, 2023
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts.

Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa

ECCV (28), 267-283, 2022
東京大学大学院情報理工学系研究科電子情報学専攻相澤・山肩・松井研究室+山崎研究室

Journal of the Virtual Reality Society of Japan, 26(3) 38-40, Sep 30, 2021
Improving The Quality Of Illustrations: Transforming Amateur Illustrations To A Professional Standard.

Keita Awane, Koki Tsubota, Hikaru Ikuta, Yusuke Matsui, Kiyoharu Aizawa, Naohiro Yanase

2021 IEEE International Conference on Image Processing(ICIP), 584-588, 2021
What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels.

Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa

CoRR (to be published at CVPR2021), abs/2103.04400, 2021
Comic Image Inpainting via Distance Transform.

Naoki Ono, Kiyoharu Aizawa, Yusuke Matsui

SA '21: SIGGRAPH Asia 2021 Technical Communications, 9-4, 2021
What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels.

Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa

IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 3113-3122, 2021
Building a Manga Dataset "Manga109" with Annotations for Multimedia Applications.

Kiyoharu Aizawa, Azuma Fujimoto, Atsushi Otsubo, Toru Ogawa, Yusuke Matsui, Koki Tsubota, Hikaru Ikuta

CoRR, abs/2005.04425, 2020
Building a Manga Dataset "Manga109" With Annotations for Multimedia Applications.

Kiyoharu Aizawa, Azuma Fujimoto, Atsushi Otsubo, Toru Ogawa, Yusuke Matsui, Koki Tsubota, Hikaru Ikuta

IEEE MultiMedia, 27(2) 8-18, 2020
Users' Preference Prediction of Real Estate Properties Based on Floor Plan Analysis.

Naoki Kato, Toshihiko Yamasaki, Kiyoharu Aizawa, Takemi Ohama

IEICE Transactions, 103-D(2) 398-405, 2020 Peer-reviewed
Conversion of Floor Plan Images to Graph Structures using Deep Learning and Application to Retrieval

YAMADA Mantaro, WANG Xueting, YAMASAKI Toshihiko, AIZAWA Kiyoharu

Proceedings of the Annual Conference of JSAI, JSAI2019 3N4J1003-3N4J1003, 2019
Object-Aware Instance Labeling for Weakly Supervised Object Detection.

Satoshi Kosugi, Toshihiko Yamasaki, Kiyoharu Aizawa

CoRR, abs/1908.03792, 2019
Zero-Shot Semantic Segmentation via Variational Mapping.

Naoki Kato, Toshihiko Yamasaki, Kiyoharu Aizawa

2019 IEEE/CVF International Conference on Computer Vision Workshops, 1363-1370, 2019
Object-Aware Instance Labeling for Weakly Supervised Object Detection.

Satoshi Kosugi, Toshihiko Yamasaki, Kiyoharu Aizawa

2019 IEEE/CVF International Conference on Computer Vision(ICCV), 6063-6071, 2019
Reinforcing the Robustness of a Deep Neural Network to Adversarial Examples by Using Color Quantization of Training Image Data.

Shuntaro Miyazato, Xueting Wang, Toshihiko Yamasaki, Kiyoharu Aizawa

2019 IEEE International Conference on Image Processing(ICIP), 884-888, 2019 Peer-reviewed
Aspect-Ratio-Preserving Multi-Patch Image Aesthetics Score Prediction.

Lijie Wang, Xueting Wang, Toshihiko Yamasaki, Kiyoharu Aizawa

IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019 Peer-reviewed
Deep Neural Network-Based Click-Through Rate Prediction using Multimodal Features of Online Banners.

Bohui Xia, Xueting Wang, Toshihiko Yamasaki, Kiyoharu Aizawa, Hiroyuki Seshime

Fifth IEEE International Conference on Multimedia Big Data(BigMM), 162-170, 2019 Peer-reviewed
Hyperlapse Generation Method for Omnidirectional Street Videos Using Adaptive Sampling

OGAWA Masanori, YAMASAKI Toshihiko, AIZAWA Kiyoharu

J101-D(7) 1052-1060, Jul 1, 2018
Similar floor plan retrieval featuring multi-task learning of layout type classification and room presence prediction

Yuki Takada, Naoto Inoue, Toshihiko Yamasaki, Kiyoharu Aizawa

2018 IEEE International Conference on Consumer Electronics, ICCE 2018, 2018- 1-6, Mar 26, 2018 Peer-reviewed

Misc.

253

Self-Play深層強化学習を用いた画像の高速非線形リサイズ—Self-Play Reinforcement Learning for Fast Image Retargeting

梶浦信勝, 小杉哲, 汪雪婷, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 119(454) 127-131, Mar, 2020
魅力度を考慮した髪型の推薦—メディアエクスペリエンス・バーチャル環境基礎

中前祐人, 王雪婷, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 119(457) 145-150, Mar, 2020
マルチモーダル深層学習によるオンライン動画広告のCTR予測—Predicting the online video advertising effectiveness with multimodal deep learning

池田純, 勢〆弘幸, 汪雪婷, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 119(454) 133-136, Mar, 2020
複数パッチ抽出によるアスペクト比を維持した画像審美度スコア予測—Aspect-Ratio-Preserving Multi-Patch Image Aesthetic Score Prediction—メディアエクスペリエンス・バーチャル環境基礎

王力捷, 汪雪テイ, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 118(502) 85-90, Mar, 2019
画像・言語特徴を用いた深層学習によるオンライン広告のクリック率予測—DNN-Based Click Through Rate Prediction Using Visual and Textual Features of Online Banners

夏博恵, 汪雪婷, 山崎俊彦, 相澤清晴, 勢〆弘幸

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 118(500) 137-142, Mar, 2019
高解像度画像の標準正規分布モデリングを可能にする段階的変分自己符号化器—マルチメディアストレージヒューマンインフォメーションメディア工学映像表現&コンピュータグラフィックス

中村遵介, 山崎俊彦, 相澤清晴

映像情報メディア学会技術報告 = ITE technical report, 43(5) 97-102, Feb, 2019
高解像度画像の標準正規分布モデリングを可能にする段階的変分自己符号化器—ITS

中村遵介, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 118(449) 97-102, Feb, 2019
スタイル転移を利用した物体検出におけるドメイン適応—Style Transfer for Domain Adaptation in Object Detection—ITS

井上直人, 古田諒佑, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 117(431) 235-238, Feb, 2018
プレゼンテーションスライドのデザインに対するCNNを用いた客観的フィードバックの生成—Objective Feedback Generation on Presentation Slide Design using CNN—マルチメディアストレージヒューマンインフォメーションメディア工学映像表現&コンピュータグラフィックス

大山真司, 山崎俊彦, 相澤清晴

映像情報メディア学会技術報告 = ITE technical report, 42(4) 223-228, Feb, 2018
招待講演深層特徴量を用いた間取り画像をクエリとする類似不動産検索—Similar Floor Plan Retrieval Featuring Multi Task Learning of Layout Type Classification and Room Presence Prediction—マルチメディアストレージヒューマンインフォメーションメディア工学映像表現&コンピュータグラフィックス

高田祐樹, 井上直人, 山崎俊彦, 相澤清晴

映像情報メディア学会技術報告 = ITE technical report, 42(4) 211-216, Feb, 2018
データドリブンなアプローチを用いた漫画画像中の吹き出しの話者推定—Speech balloon and speaker association by data driven approach—ITS

山本和慶, 小川徹, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 117(431) 287-292, Feb, 2018
データドリブンなアプローチを用いた漫画画像中の吹き出しの話者推定—Speech balloon and speaker association by data driven approach—マルチメディアストレージヒューマンインフォメーションメディア工学映像表現&コンピュータグラフィックス

山本和慶, 小川徹, 山崎俊彦, 相澤清晴

映像情報メディア学会技術報告 = ITE technical report, 42(4) 287-292, Feb, 2018
プレゼンテーションスライドのデザインに対するCNNを用いた客観的フィードバックの生成—Objective Feedback Generation on Presentation Slide Design using CNN—画像工学

大山真司, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 117(432) 223-228, Feb, 2018
スタイル転移を利用した物体検出におけるドメイン適応—Style Transfer for Domain Adaptation in Object Detection—マルチメディアストレージヒューマンインフォメーションメディア工学映像表現&コンピュータグラフィックス

井上直人, 古田諒佑, 山崎俊彦, 相澤清晴

映像情報メディア学会技術報告 = ITE technical report, 42(4) 235-238, Feb, 2018
ジオタグ付き画像を利用した単眼カメラの高精度位置推定—Monocular Camera Localization using Geo-tagged Images—ITS

石見和也, 池畑諭, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 117(431) 229-234, Feb, 2018
並列化された検出器による高精度漫画物体検出—Forked Object Detector for Manga Objects—マルチメディアストレージヒューマンインフォメーションメディア工学映像表現&コンピュータグラフィックス

小川徹, 山崎俊彦, 相澤清晴

映像情報メディア学会技術報告 = ITE technical report, 42(4) 293-298, Feb, 2018
ジオタグ付き画像を利用した単眼カメラの高精度位置推定—Monocular Camera Localization using Geo-tagged Images—マルチメディアストレージヒューマンインフォメーションメディア工学映像表現&コンピュータグラフィックス

石見和也, 池畑諭, 山崎俊彦, 相澤清晴

映像情報メディア学会技術報告 = ITE technical report, 42(4) 229-234, Feb, 2018
招待講演深層特徴量を用いた間取り画像をクエリとする類似不動産検索—Similar Floor Plan Retrieval Featuring Multi Task Learning of Layout Type Classification and Room Presence Prediction—画像工学

高田祐樹, 井上直人, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 117(432) 211-216, Feb, 2018
並列化された検出器による高精度漫画物体検出—Forked Object Detector for Manga Objects—画像工学

小川徹, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 117(432) 293-298, Feb, 2018
Product and Service Popularity Analysis and Class Discovery on Instagram (メディアエクスペリエンス・バーチャル環境基礎)

張軼威, 山崎俊彦, 相澤清晴

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 117(217) 13-18, Sep 21, 2017

Research Projects

Fundamental Technologies for Deep Fake Detection

Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B), Grant-in-Aid for Scientific Research (B), Japan Society for the Promotion of Science, Apr, 2022 - Mar, 2025
Elucidation of age-related macular degeneration pathology by fundus image and cytokine concentrations using artificial intelligence

Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C), Grant-in-Aid for Scientific Research (C), Japan Society for the Promotion of Science, Apr, 2021 - Mar, 2024
The longitudinal study on the effects of early childhood education and care on child development

Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (S), Grant-in-Aid for Scientific Research (S), Japan Society for the Promotion of Science, Jun, 2019 - Mar, 2024
Machine Learning with Small Data

Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Research (Exploratory), Grant-in-Aid for Challenging Research (Exploratory), Japan Society for the Promotion of Science, Jun, 2019 - Mar, 2022

Yamasaki Toshihiko
Assistance of multi-media contents generation for supporting learning and teaching of craftsmanship at home

Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C), Grant-in-Aid for Scientific Research (C), Japan Society for the Promotion of Science, Apr, 2018 - Mar, 2022
Fundamental Technologies for Information Sharing and Behavior Change Actuation in SNSs

Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B), Grant-in-Aid for Scientific Research (B), Japan Society for the Promotion of Science, Apr, 2018 - Mar, 2021

Yamasaki Toshihiko
Content Generation Navigation Based on Big Multimedia Processing

Grants-in-Aid for Scientific Research Grant-in-Aid for Young Scientists (A), Grant-in-Aid for Young Scientists (A), Japan Society for the Promotion of Science, Apr, 2014 - Mar, 2018

Yamasaki Toshihiko
Fusion of Object Recognition and Material Recognition for Smarter Image Recognition

Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Exploratory Research, Grant-in-Aid for Challenging Exploratory Research, Japan Society for the Promotion of Science, Apr, 2014 - Mar, 2017

Yamasaki Toshihiko, AIZAWA Kiyoharu
Development of treatment planning system for neck node metastases

Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C), Grant-in-Aid for Scientific Research (C), Japan Society for the Promotion of Science, Apr, 2013 - Mar, 2016

MURAKAMI RYUJI, HIRAI Toshinori, UCHIYAMA Yoshikazu, TOYA Ryo, NAKAYAMA Hideki, MURAKAMI Daizo, YAGI Masakazu, YAMASAKI Toshihiko
Compression of time-varying 3D meshes based on patch-based matching

Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Exploratory Research, Grant-in-Aid for Challenging Exploratory Research, Japan Society for the Promotion of Science, 2010 - 2012

YAMASAKI Toshihiko, AIZAWA Kiyoharu
Lifelog Infrastructure : Capture, Processing, Sharing

Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (A), Grant-in-Aid for Scientific Research (A), Japan Society for the Promotion of Science, 2008 - 2011

AIZAWA Kiyoharu, YAMASAKI Toshihiko, MORIKAWA Chamin
3次元映像の検索・編集に関する研究

科学研究費助成事業萌芽研究, 萌芽研究, 日本学術振興会, 2007 - 2008

山崎俊彦, 相澤清晴
Functional Surveillance System Capturing Wide-Angle and Close-Up Views

Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B), Grant-in-Aid for Scientific Research (B), Japan Society for the Promotion of Science, 2005 - 2006

AIZAWA Kiyoharu, YAMASAKI Toshihiko
3次元モデルの質感表現・動的変化の圧縮に関する研究

科学研究費助成事業若手研究(B), 若手研究(B), 日本学術振興会, 2005 - 2006

山崎俊彦