Responsive image



東京大学 大学院情報理工学系研究科 電子情報学専攻

私は東京大学にて研究を進めている講師です. 私の研究分野はコンピュータビジョン,マルチメディア処理です.特に,大規模データ探索(画像検索,近似最近傍探索)を専門としています

〒113-8656 東京都文京区本郷 7-3-1 工学部2号館 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


  • 小野 直樹 (M2)
  • 山下 陸 (M2)
  • 李 映萱 (M2)
  • 付 彦源 (M2)
  • 金海 智大 (M1)
  • 加古 遼太郎 (M1)
  • 東 大樹 (B4)
  • 熊谷 はるか (B4)
  • 佐藤 篤樹 (B4)
  • 奈良 亮耶 (B4)

  • 大橋 実咲 (2021-2022, B4)
  • 松岡 暉心 (2021-2022, B4)
  • 久留 陽一郎 (2020-2021, B4)



  • メディアコンピューティング実践(2022
  • ソフトウェア1(2020, 2021, 2022


ARM 4-bit PQ

Yusuke Matsui, Yoshiki Imaizumi, Naoya Miyamoto, and Naoki Yoshifuji
Implemented in Faiss: issue, PR

Paper Blog by Imaizumi Blog by Matsui

Image Retrieval in the Wild

Yusuke Matsui, Takuma Yamaguchi, and Zheng Wang
CVPR 2020 Tutorial


Reconfigurable Inverted Index

Yusuke Matsui, Ryota Hinami, and Shin'ichi Satoh
ACMMM 2018 (oral, acceptance rate: 8.45%)

Paper Project Code Slides Poster


松井勇佑, 内田祐介, Hervé Jégou, and 佐藤真一
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


招待講演:1時間で画像検索エンジンを作る, CGVI研究会, 2017
Image Retrieval in the Wild, CVPR Tutorial, 2020

Project Slide Slide (Jp) Code Demo Video

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

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, 2017

Paper Project

Illustration2Vec: A Semantic Vector Representation of Illustrations

Masaki Saito and Yusuke Matsui
ACM SIGGRAPH Asia, Technical Brief, 2015

Paper Project

Separation of Manga Line Drawing and Screentones

Kota Ito, Yusuke Matsui, Toshihiko Yamasaki, and Kiyoharu Aizawa
Eurographics, Short paper, 2015


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





Technical report



  • annbench: Simple and lightweight benchmark for approximate nearest neighbor search in python
  • manga109api: Simple python API to read annotation data of Manga109
  • Rii: Fast and memory-efficient ANN with a subset-search functionality
  • nanopq: Pure python implementation of product quantization for nearest neighbor search
  • PQk-means: Fast and memory-efficient clustering
  • faiss_tips: Some useful tips for faiss
  • PQTable: Fast search algorithm for product-quantized codes via hash-tables
  • Simple image search engine
  • Manga109: A dataset of manga (Japanese comics)

Last updated: January 3, 2023