Postdoctoral researcher
National Institute of Informatics (NII), Japan

: Shin'ichi Satoh Laboratory, National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan

: matsui(at)nii.ac.jp / : Resume / : Google scholar / : Github / : kaggle

I am a postdoctoral researcher at National Institute of Informatics (NII) in Japan, working in Prof. Shin'ichi Satoh's group. I received my Ph.D. from the University of Tokyo in 2016 under the supervision of Prof. Kiyoharu Aizawa. My research interest includes computer vision and multimedia processing. More specifically, I am interested in theory and applications of image retrieval and manga/comic image processing.

News

Projects



Coming soon...


Reconfigurable Inverted Index
Yusuke Matsui, Ryota Hinami, and Shin'ichi Satoh
ACMMM 2018 (oral).
[Paper] [Project] [Code]

A Survey of Product Quantization
Yusuke Matsui, Yusuke Uchida, Hervé Jégou, Shin'ichi Satoh
ITE Transactions on Media Technology and Applications 2018.
[Paper] [Project]

PQk-means: Billion-scale Clustering for Product-quantized Codes
Yusuke Matsui* , Keisuke Ogaki* , Toshihiko Yamasaki, and Kiyoharu Aizawa
*Joint first authors.
ACMMM 2017.
[Paper] [Project] [Code] [News release]


PQTable: Nonexhaustive Fast Search for Product-Quantized Codes Using Hash Tables
Yusuke Matsui , Toshihiko Yamasaki, and Kiyoharu Aizawa
ICCV 2015, TMM 2018.
[Paper] [Project] [Code]

Writing an Image Search Engine from Scratch
Yusuke Matsui
One-hour hands-on seminar at CGVI, 2017.
[Project] [Slide (in Japanese)] [Code] [Demo]

DrawFromDrawings: 2D Drawing Assistance via Stroke Interpolation with a Sketch Database
Yusuke Matsui , Takaaki Shiratori, and Kiyoharu Aizawa
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2017.
[Paper] [Project] [Video (YouTube)]

Sketch-based Manga Retrieval using Manga109 Dataset
Yusuke Matsui , Kota Ito, Yuji Aramaki, Azuma Fujimoto, Toru Ogawa, Toshihiko Yamasaki, and Kiyoharu Aizawa
Multimedia Tools and Applications (MTAP), Springer (in press).
[Paper] [Project] [Springer]

Illustration2Vec: A Semantic Vector Representation of Illustrations
Masaki Saito and Yusuke Matsui
ACM SIGGRAPH Asia, Technical Brief, 2015.
[Paper] [Project] [Pre-trained model] [ACM]

Separation of Manga Line Drawing and Screentones
Kota Ito, Yusuke Matsui , Toshihiko Yamasaki, and Kiyoharu Aizawa
Eurographics, Short paper, 2015.
[Code]

Reference-based Manga Colorization by Graph Correspondence Using Quadratic Programming
Kazuhiro Sato, Yusuke Matsui , Toshihiko Yamasaki, and Kiyoharu Aizawa
ACM SIGGRAPH Asia, Technical Briefs, 2014.
[Paper] [ACM]

Publications

Journal

  • Yusuke Matsui, Yusuke Uchida, Hervé Jégou, Shin'ichi Satoh
    A Survey of Product Quantization
    ITE Transactions on Media Technology and Applications (ITE), 2018. [pdf]
  • Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    PQTable: Nonexhaustive Fast Search for Product-Quantized Codes Using Hash Tables
    IEEE Transactions on Multimedia (TMM), 2018. [pdf] [project]
  • Yusuke Matsui, Kota Ito, Yuji Aramaki, Azuma Fujimoto, Toru Ogawa, Toshihiko Yamasaki, Kiyoharu Aizawa
    Sketch-based Manga Retrieval using Manga109 Dataset
    Multimedia Tools and Applications (MTAP), 2017. [pdf] [project]
  • Yusuke Matsui, Takaaki Shiratori, Kiyoharu Aizawa
    DrawFromDrawings: 2D Drawing Assistance via Stroke Interpolation with a Sketch Database
    IEEE Transactions on Visualization and Computer Graphics (TVCG), 2017. [pdf] [project]

Conference

  • Yusuke Matsui, Shin'ichi Satoh
    Revisiting Column-Wise Vector Quantization for Memory-Efficient Matrix Multiplication
    IEEE International Conference on Image Processing (ICIP), 2018.
  • Yusuke Matsui, Ryota Hinami, Shin'ichi Satoh
    Reconfigurable Inverted Index
    ACM International Conference on Multimedia (ACMMM), 2018.
  • Chairath Sirirattanapol, Yusuke Matsui, Shin'ichi Satoh, Kuninori Matsuda, Kazuaki Yamamoto
    Deep Image Retrieval Applied on Kotenseki Ancient Japanese Literature
    IEEE International Workshop on Machine Learning and Computing for Visual Semantic Analysis (MLCSA), 2017. [project]
  • Junfu Pu, Yusuke Matsui, Fan Yang, Shin'ichi Satoh
    Energy based Fast Event Retrieval in Video with Temporal Match Kernel
    IEEE International Conference on Image Processing (ICIP), 2017.
  • Yusuke Matsui, Keisuke Ogaki, Toshihiko Yamasaki, Kiyoharu Aizawa
    PQk-means: Billion-scale Clustering for Product-quantized Codes
    ACM International Conference on Multimedia (ACMMM), 2017. [pdf] [project]
  • Ryota Hinami, Yusuke Matsui, Shin'ichi Satoh
    Region-based Image Retrieval Revisited
    ACM International Conference on Multimedia (ACMMM), 2017. [pdf]
  • Azuma Fujimoto, Toru Ogawa, Kazuyoshi Yamamoto, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Manga109 Dataset and Creation of Metadata
    International Workshop on Comics Analysis, Processing and Understanding (MANPU), 2016.
  • Kota Ito, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Interactive Region Segmentation for Manga
    International Conference on Pattern Recognition (ICPR), 2016.
  • Toru Ogawa, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Sketch Simplification by Classifying Strokes
    International Conference on Pattern Recognition (ICPR), 2016.
  • Yuji Aramaki, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Text Detection in Manga by Combining Connected-omponent-based and Region-based Classifications
    IEEE International Conference on Image Processing (ICIP), 2016.
  • Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization using Hash Tables
    IEEE International Conference on Computer Vision (ICCV), 2015. [pdf] [project]
  • Kota Ito, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Separation of Manga Line Drawings and Screentones
    Eurographics, Short Paper, 2015. [project]
  • Yuji Aramaki, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Interactive Segmentation for Manga using Lossless Thinning and Coarse Labeling
    APSIPA ASC, 2015.
  • Masaki Saito, Yusuke Matsui
    Illustration2vec: A Semantic Vector Representation of Illustrations
    ACM SIGGRAPH Asia, Technical Brief, 2015. [project]
  • Yusuke Matsui
    Challenge for Manga Processing: Sketch-based Manga Retrieval
    ACM International Conference on Multimedia (ACMMM), Doctoral Symposium, 2015. [project]
  • Yusuke Matsui, Kiyoharu Aizawa, Yushi Jing
    Sketch2Manga: Sketch-based Manga Retrieval
    IEEE International Conference on Image Processing (ICIP), 2014. [pdf] [project]
  • Saemi Choi, Yusuke Matsui, Kiyoharu Aizawa
    Diffusion : Change an Ambience of the Space with a Small Amount of Ink
    ACM SIGGRAPH Asia, Poster, 2014.
  • Kazuhiro Sato, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Reference based Manga Colorization by Graph Correspondence Using Quadratic Programming
    ACM SIGGRAPH Asia, Technical Brief, 2014. [pdf]
  • Daiki Matsumoto, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa, Takanori Katagiri
    IllustStyleMap: Visualization of Illustrations based on Similarity of Drawing Style of Authors
    ACM SIGGRAPH, Poster, 2014.
  • Yuji Aramaki, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Interactive Segmentation for Manga
    ACM SIGGRAPH, Poster, 2014.
  • Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Interactive Manga Retargeting
    ACM SIGGRAPH, Poster, 2011. [pdf]

Technical report

  • Toru Ogawa, Atsushi Otsubo, Rei Narita, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    Object Detection for Comics using Manga109 Annotations
    CoRR, 2018. [project]
  • Yasunori Kudo, Keisuke Ogaki, Yusuke Matsui, Yuri Odagiri
    Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations
    CoRR, 2018. [project]
  • Yusuke Matsui, Keisuke Ogaki, Kiyoharu Aizawa, Toshihiko Yamasaki
    PQk-means: Billion-scale Clustering for Product-quantized Codes
    CoRR, 2017. [project]
  • Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
    PQTable: Non-exhaustive Fast Search for Product-quantized Codes using Hash Tables
    CoRR, 2017. [project]
  • Yusuke Matsui, Kota Ito, Yuji Aramaki, Toshihiko Yamasaki, Kiyoharu Aizawa
    Sketch-based Manga Retrieval using Manga109 Dataset
    CoRR, 2015. [project]

Awards

  • Funai Research Award, Funai Foundation for Information Technology, 2018. [link]
  • Student Best Paper Award, IEEE Signal Processing Society Japan, 2016.
  • Quick Report on Doctoral Theses Recommended by SIGs, IPSJ, 2016.
  • Dean's Award, Graduate School of Information Science and Technology, The University of Tokyo, 2016.
  • Best Student Paper Award, IMPS, 2015.
  • Best Interactive Presentation Award, HCG Symposium, 2014.
  • Dean's Award, Graduate School of Interdisciplinary Information Studies, The University of Tokyo, 2013.
  • Harashima Hiroshi Science Award, Association for Promotion of Electrical, Electronic and Information Engineering, 2012.
  • Dean's Award, Faculty of Engineering, The University of Tokyo, 2011.
  • 7th place, Google Landmark Recognition Challenge, 2018. [link]
  • 7th place, Google Landmark Retrieval Challenge, 2018. [link]
  • Outstanding Reviewer Award, ACM ICMR, 2018. [link]
  • ACM Student Research Competition 3rd Place, ACM SIGGRAPH, 2011.

Funding sources

  • ACT-I (Advanced), JST. (2018/4 - 2020/3)
  • Joint Research, Dwango. (2016/12 - 2017/3)
  • ACT-I, JST. (2016/12 - 2018/3)
  • Research Activity Start-up, JSPS. (2016/10 - 2018/3)
  • Research Fellowship for Young Scientists (DC1), JSPS. (2013/4 - 2016/5)

Link