• Yingxuan Li (D2)
• Yusuke Kondo (D2)
• Hiroki Azuma (M2)
• Atsuki Sato (M2)
• Kunato Nishina (M2)
• Ryoya Nara (M1)
• Fuma Hidaka (M1)
• Yutaro Oguri (M1)
• Tomohisa Takeda (B4)
• Kyosuke Nishishita (B4)
• Tomohiro Yamashita (B4)

Past members

• [ 2024.10 ] One paper has been accepted for NeurIPS 2024 WS!
• [ 2024.09 ] Three papers have been accepted for ECCV 2024 WS!
• [ 2024.09 ] Yingxuan Li (D2) was featured in the introduction video of the Graduate School of Information Science and Technology at the University of Tokyo!
• [ 2024.07 ] Our paper has been accepted for ACMMM 2024 (Oral)!
• [ 2024.04 ] Our papers have been accepted for ICME 2024 and CVPR WS 2024!
• [ 2024.03 ] Yutaro has received the Dean's Award!
• [ 2024.03 ] Matsui has received the Best Teaching Award from the Faculty of Engineering.
• [ 2023.10 ] Congratulations to Hiroki on winning the Best Paper Award at the AROW Workshop at ICCV 23!
• [ 2023.09 ] Our paper has been accepted for NeurIPS 2023!
• [ 2023.08 ] We achieved second place in several categories at the SISAP 2023 Indexing Challenge! [Results][Report]
• [ 2023.08 ] One paper has been accepted for ACMMM 2023, and another paper has been accepted for ICCV 2023 WS!
• [ 2023.05 ] We will introduce Matsui-lab at the Entrance Examination Briefing on May 20. Matsui-lab will accept master's and doctoral students.
• [ 2023.04 ] We have released a website for AIP acceleration project: High-performance Data Science.
• [ 2023.04 ] Our tutorial got accepted at CVPR 2023. Neural Search in Action, with Martin and Han.
• [ 2023.03 ] Atsuki received the Outstanding Graduation Thesis Award from the Department of Information and Communication Engineering!
• [ 2023.01 ] Updated "For prospective students".
• [ 2022.05 ] We introduced Matsui-lab at the Entrance Examination Briefing. Matsui-lab will accept master's and doctoral students.
• [ 2022.01 ] Our paper has been accepted for ICASSP!
• [ 2021.10 ] Our paper has been accepted for BMVC!
• [ 2021.09 ] Our paper has been accepted for SIGGRAPH Asia Technical Communications!
• [ 2021.06 ] Our team (I and Fixstars) implemented the 4-bit PQ algorithm on ARM for the faiss library, enabling 60x speedup. [issue] [PR] [blog by Imaizumi (in Japanese)] [blog by Matsui (in Japanese)]
• [ 2021.05 ] I was selected as an outstanding reviewer for CVPR 2021.
• [ 2021.01 ] Updated: For prospective students.
• [ 2020.12 ] Our paper on manga translation has been accepted for AAAI2021. [pdf], [dataset]
• [ 2020.10 ] Check out our ACMMM tutorial, Effective and Efficient: Toward Open-world Instance Re-identification, with Zheng, Wu, and Shin'ichi!
• [ 2020.06 ] Check out our CVPR tutorial, Image Retrieval in the Wild, from 8:30am on June 19th (PDT). This event is being held remotely on Zoom. Anyone can attend it with CVPR registration.
• [ 2020.05 ] We will introduce Matsui-lab at the Entrance Examination Briefing on May 23. Matsui-lab will accept master's and doctoral students.
• [ 2020.04 ] I joined the Department of Information and Communication Engineering, Graduate School of Information Science and Technology, at the University of Tokyo as a Lecturer (Assistant Professor). I will run the Aizawa-Yamasaki-Matsui Lab
• [ 2020.03 ] Our tutorial got accepted at CVPR 2020. Image Retrieval in the Wild, with Zheng and Takuma.
• [ 2020.03 ] A benchmark for approximate nearest neighbor search called annbench is now available. Please give it a try.
• [ 2019.09 ] My research proposal was accepted to JST Sakigake.
• [ 2019.06 ] We will organize a workshop at ICCV 2019.
• [ 2019.01 ] Joined the Institute of Industrial Science at the University of Tokyo as an Assistant Professor.
• [ 2018.10 ] Slides and a poster of Reconfigurable Inverted Index are now available.
• [ 2018.09 ] Manga109 API was released. You can install it via $ pip install manga109api
• [ 2018.08 ] Our new project "Mantra: Fast and Accurate Automatic Translation for Manga" (with Shonosuke Ishiwatari and Ryota Hinami) was awarded in Innovative Technologies 2018! release (in Japanese), video (in Japanese).
• [ 2018.08 ] Paper, code, and project page for Reconfigurable Inverted Index (ACMMM18, oral) are now available. You can install the Rii python package via $ pip install rii !
• [ 2018.07 ] nanopq: pure python implementation of PQ/OPQ was released. You can install it via $ pip install nanopq
• [ 2018.07 ] One full paper was accepted to ACM Multimedia 2018 for an oral presentation!
• [ 2018.06 ] I wrote a chapter of a textbook (in Japanese).
• [ 2018.06 ] I received an Outstanding Reviewer Award at ICMR 2018.
• [ 2018.05 ] Our team attended the Google Landmark Competition, and got 7th place for both Retrieval Challenge (in 209 teams) and Recognition Challenge (in 483 teams)!
• [ 2018.04 ] I received a Funai Research Award.
• [ 2018.01 ] Our survey paper on PQ is available.
• [ 2017.11 ] An extended version of our ICCV work (PQTable) was accepted to IEEE Transactions on Multimedia.
• [ 2017.09 ] Paper, code, and project page for PQk-means (ACMMM17) are now available. You can install the pqkmeans python library via $ pip install pqkmeans !
• [ 2017.07 ] ACM Multimedia 2017 papers on the web is opened.
• [ 2017.07 ] Two full papers were accepted to ACM Multimedia 2017.
• [ 2017.03 ] Will give a lecture, "Writing an Image Search Engine from Scrach", at CGVI on March 13. [web] [project]
• [ 2016.12 ] Will visit Osaka University for a talk about PQ and binary hashing on Dec 2. [lecture note (in Japanese)]
• [ 2016.11 ] My research proposal was accepted to JST ACT-I.
• [ 2016.11 ] I received an IEEE Signal Processing Society Japan Student Paper Award.
• [ 2016.08 ] My PhD dissertation is selected for IPSJ Quick Report on Doctoral Theses Recommended by SIGs (in Japanese).

• Non-Research Tips for Information Science Researchers (2024)
• Media Computing in Practice (2022)

• For prospective students If you are interested in joining Matsui Lab, please read this.
• The Missing Semester of Your CS Education (Japanese edition) I supervised the translation of the course

Broadcast Product

Yusuke Matsui and Tatsuya Yokota
arXiv 2024

Paper Blog

High-Performance Data Science

Yusuke Matsui, Daichi Amagata, Hiroaki Shiokawa, and Mai Nishimura
AIP Acceleration Research

Project

Neural Search in Action

Yusuke Matsui, Martin Aumüller, and Han Xiao
CVPR 2023 Tutorial

Tutorial

ARM 4-bit PQ

Yusuke Matsui, Yoshiki Imaizumi, Naoya Miyamoto, and Naoki Yoshifuji
ICASSP 2022
Implemented in Faiss: issue, PR

Paper Blog by Imaizumi Blog by Matsui

Old projects

Image Retrieval in the Wild

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

Tutorial

Reconfigurable Inverted Index

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

Paper Project Code Slides Poster

A Survey of Product Quantization

Yusuke Matsui, Yusuke Uchida, Hervé Jégou, and 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

Kotenseki Image Search

Yusuke Matsui, Chairath Sirirattanapol, Shin'ichi Satoh, Kuninori Matsuda, and Kazuaki Yamamoto

Project Kotenseki dataset 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
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

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

Old slides

Journal

• Unbiased Scene Graph Generation Using Predicate Similarities
  Yusuke Matsui, Misaki Ohashi
  IEEE Access, 2024 pdf
• Subset Retrieval Nearest Neighbor Machine Translation
  Hiroyuki Deguchi, Taro Watanabe, Yusuke Matsui, Masao Utiyama, Hideki Tanaka, Eiichiro Sumita
  Journal of Natural Language Processing, 2024
• Face Detection, Tracking, and Classification from Large-Scale News Archives for Analysis of Key Political Figures
  Andreu Girbau, Tetsuro Kobayashi, Benjamin Renoust, Yusuke Matsui, Shin'ichi Satoh
  Political Analysis, 2024 pdf
• 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, 2020
• PQTable: Nonexhaustive Fast Search for Product-Quantized Codes Using Hash Tables
  Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  IEEE Transactions on Multimedia (TMM), 2018 project pdf
• A Survey of Product Quantization
  Yusuke Matsui, Yusuke Uchida, Hervé Jégou, Shin'ichi Satoh
  ITE Transactions on Media Technology and Applications (ITE), 2018 pdf
• DrawFromDrawings: 2D Drawing Assistance via Stroke Interpolation with a Sketch Database
  Yusuke Matsui, Takaaki Shiratori, Kiyoharu Aizawa
  IEEE Transactions on Visualization and Computer Graphics (TVCG), 2017 project pdf
• Sketch-based Manga Retrieval using Manga109 Dataset
  Yusuke Matsui, Kota Ito, Yuji Aramaki, Azuma Fujimoto, Toru Ogawa, Toshihiko Yamasaki, Kiyoharu Aizawa
  Multimedia Tools and Applications (MTAP), 2017 project pdf

Conference

• Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion
  Yingxuan Li, Ryota Hinami, Kiyoharu Aizawa, Yusuke Matsui
  ACM International Conference on Multimedia (ACMMM), Oral, 2024 project pdf
• SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities
  Kunato Nishina, Yusuke Matsui
  Computer Vision and Pattern Recognition Conference, Workshop on Graphic Design Understanding and Generation (CVPR WS (GDUG)), Extended Abstract, 2024 project pdf
• ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer
  Hiroki Azuma, Yusuke Matsui, Atsuto Maki
  European Conference on Computer Vision, Workshop on Out Of Distribution Generalization in Computer Vision (ECCV WS (OOD-CV)), 2024 project pdf
• High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis
  Takuto Onikubo, Yusuke Matsui
  European Conference on Computer Vision, Workshop on The Dark Side of Generative AIs and Beyond (ECCV WS (Dark Side of GenAI and Beyond)), Oral, 2024 project pdf
• Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval
  Ryoya Nara, Yu-Chieh Lin, Yuji Nozawa, Youyang Ng, Goh Itoh, Osamu Torii, Yusuke Matsui
  European Conference on Computer Vision, Workshop on Traditional Computer Vision in the Age of Deep Learning (ECCV WS (TradiCV)), Oral, 2024 pdf
• Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection
  Yingxuan Li, Kiyoharu Aizawa, Yusuke Matsui
  IEEE International Conference on Multimedia and Expo (ICME), 2024 project pdf
• Cross-Lingual Learning in Multilingual Scene Text Recognition
  Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
  International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024 project pdf
• FlexFlood: Efficiently Updatable Learned Multi-dimensional Index
  Fuma Hidaka, Yusuke Matsui
  Neural Information Processing Systems, Workshop on ML for Systems (NeurIPS WS (MLforSys)), 2024 project pdf
• Relative NN-Descent: A Fast Index Construction for Graph-Based Approximate Nearest Neighbor Search
  Naoki Ono, Yusuke Matsui
  ACM International Conference on Multimedia (ACMMM), 2023 project pdf
• Subset Retrieval Nearest Neighbor Machine Translation
  Hiroyuki Deguchi, Taro Watanabe, Yusuke Matsui, Masao Utiyama, Hideki Tanaka, Eiichiro Sumita
  Association for Computational Linguistics (ACL), 2023 project pdf
• Character Image Combination for Multilingual Scene Text Recognition: Can We Make High-Performance Synthetic Data Without Fonts?
  Jeonghun Baek, Eunchung Noh, Yusuke Matsui, Kiyoharu Aizawa
  International Conference on Computer Vision, Workshop Towards the Next Generation of Computer Vision Datasets (ICCV WS (TNGCV)), 2023
• Defense-Prefix for Preventing Typographic Attacks on CLIP
  Hiroki Azuma, Yusuke Matsui
  International Conference on Computer Vision, Workshop on Adversarial Robustness In the Real World (ICCV WS (AROW)), Best Paper Award, 2023 project pdf
• General and Practical Tuning Method for Off-the-Shelf Graph-Based Index
  Yutaro Oguri, Yusuke Matsui
  International Conference on Similarity Search and Applications (SISAP), Indexing Challenge Report by Team Utokyo, 2023 project pdf
• Fast Partitioned Learned Bloom Filter
  Atsuki Sato, Yusuke Matsui
  Neural Information Processing Systems (NeurIPS), 2023 project pdf
• COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
  Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
  European Conference on Computer Vision (ECCV), 2022 project pdf
• Translation of Illustration Artist Style using Sailormoonredraw Data
  Keita Awane, Daichi Horita, Hikaru Ikuta, Yusuke Matsui, Kiyoharu Aizawa, Naohiro Yanase
  IEEE International Conference on Image Processing (ICIP), 2022
• ARM 4-bit PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM
  Yusuke Matsui, Yoshiki Imaizumi, Naoya Miyamoto, Naoki Yoshifuji
  International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 pdf
• Towards Content-Aware Pixel-Wise Comic Panel Segmentation
  Hikaru Ikuta, Runtian Yu, Yusuke Matsui, Kiyoharu Aizawa
  International Workshop on Comics Analysis, Processing and Understanding (MANPU), 2022
• Towards Fully Automated Manga Translation
  Ryota Hinami, Shonosuke Ishiwatari, Kazuhiko Yasuda, Yusuke Matsui
  AAAI Conference on Artificial Intelligence (AAAI), 2021 project pdf
• Comic Image Inpainting via Distance Transform
  Naoki Ono, Kiyoharu Aizawa, Yusuke Matsui
  ACM SIGGRAPH Asia, Technical Communications, 2021
• Cascading Feature Extraction for Fast Point Cloud Registration
  Yoichiro Hisadome, Yusuke Matsui
  British Machine Vision Conference (BMVC), 2021 project pdf
• What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
  Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
  Conference on Computer Vision and Pattern Recognition (CVPR), 2021 pdf
• Improving the Quality of Illustrations: Transforming Amateur Illustrations to a Professional Standard
  Keita Awane, Koki Tsubota, Hikaru Ikuta, Yusuke Matsui, Kiyoharu Aizawa, Naohiro Yanase
  IEEE International Conference on Image Processing (ICIP), 2021
• Efficient Nearest Neighbor Search by Removing Anti-hub
  Kimihiro Tanaka, Yusuke Matsui, Shin'ichi Satoh
  International Conference on Multimedia Retrieval (ICMR), 2021
• Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing
  Fan Yang, Ryota Hinami, Yusuke Matsui, Steven Ly, Shin'ichi Satoh
  AAAI Conference on Artificial Intelligence (AAAI), 2019 project pdf
• Evaluating Face Tracking for Political Analysis in Japanese News Over a Long Period of Time
  Haolin Ren, Fan Yang, Benjamin Renoust, Yusuke Matsui, Tetsuro Kobayashi, Shin'ichi Satoh
  IEEE/WIC/ACM International Conference on Web Intelligence (WI), 2019
• Reconfigurable Inverted Index
  Yusuke Matsui, Ryota Hinami, Shin'ichi Satoh
  ACM International Conference on Multimedia (ACMMM), Oral, 2018 project pdf
• Revisiting Column-Wise Vector Quantization for Memory-Efficient Matrix Multiplication
  Yusuke Matsui, Shin'ichi Satoh
  IEEE International Conference on Image Processing (ICIP), 2018
• PQk-means: Billion-scale Clustering for Product-quantized Codes
  Yusuke Matsui, Keisuke Ogaki, Toshihiko Yamasaki, Kiyoharu Aizawa
  ACM International Conference on Multimedia (ACMMM), 2017 project pdf
• Region-based Image Retrieval Revisited
  Ryota Hinami, Yusuke Matsui, Shin'ichi Satoh
  ACM International Conference on Multimedia (ACMMM), Oral, 2017 pdf
• Energy based Fast Event Retrieval in Video with Temporal Match Kernel
  Junfu Pu, Yusuke Matsui, Fan Yang, Shin'ichi Satoh
  IEEE International Conference on Image Processing (ICIP), 2017
• Deep Image Retrieval Applied on Kotenseki Ancient Japanese Literature
  Chairath Sirirattanapol, Yusuke Matsui, Shin'ichi Satoh, Kuninori Matsuda, Kazuaki Yamamoto
  IEEE International Workshop on Machine Learning and Computing for Visual Semantic Analysis (MLCSA), 2017 project
• Text Detection in Manga by Combining Connected-omponent-based and Region-based Classifications
  Yuji Aramaki, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  IEEE International Conference on Image Processing (ICIP), 2016
• Sketch Simplification by Classifying Strokes
  Toru Ogawa, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  International Conference on Pattern Recognition (ICPR), 2016
• Interactive Region Segmentation for Manga
  Kota Ito, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  International Conference on Pattern Recognition (ICPR), 2016
• Manga109 Dataset and Creation of Metadata
  Azuma Fujimoto, Toru Ogawa, Kazuyoshi Yamamoto, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  International Workshop on Comics Analysis, Processing and Understanding (MANPU), 2016
• Challenge for Manga Processing: Sketch-based Manga Retrieval
  Yusuke Matsui
  ACM International Conference on Multimedia (ACMMM), Doctoral Symposium, 2015 project
• Illustration2vec: A Semantic Vector Representation of Illustrations
  Masaki Saito, Yusuke Matsui
  ACM SIGGRAPH Asia, Technical Brief, 2015 project
• Interactive Segmentation for Manga using Lossless Thinning and Coarse Labeling
  Yuji Aramaki, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  APSIPA ASC, 2015
• Separation of Manga Line Drawings and Screentones
  Kota Ito, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  Eurographics, Short Paper, 2015 project
• PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization using Hash Tables
  Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  IEEE International Conference on Computer Vision (ICCV), 2015 project pdf
• Interactive Segmentation for Manga
  Yuji Aramaki, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  ACM SIGGRAPH, Poster, 2014
• IllustStyleMap: Visualization of Illustrations based on Similarity of Drawing Style of Authors
  Daiki Matsumoto, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa, Takanori Katagiri
  ACM SIGGRAPH, Poster, 2014
• Reference based Manga Colorization by Graph Correspondence Using Quadratic Programming
  Kazuhiro Sato, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  ACM SIGGRAPH Asia, Technical Brief, 2014 pdf
• Diffusion : Change an Ambience of the Space with a Small Amount of Ink
  Saemi Choi, Yusuke Matsui, Kiyoharu Aizawa
  ACM SIGGRAPH Asia, Poster, 2014
• Sketch2Manga: Sketch-based Manga Retrieval
  Yusuke Matsui, Kiyoharu Aizawa, Yushi Jing
  IEEE International Conference on Image Processing (ICIP), 2014 project pdf
• Interactive Manga Retargeting
  Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  ACM SIGGRAPH, Poster, 2011 pdf

Technical report

• Theoretical and Empirical Analysis of Adaptive Entry Point Selection for Graph-based Approximate Nearest Neighbor Search
  Yutaro Oguri, Yusuke Matsui
  arXiv, 2024 pdf
• ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer
  Hiroki Azuma, Yusuke Matsui, Atsuto Maki
  arXiv, 2024 pdf
• SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities
  Kunato Nishina, Yusuke Matsui
  arXiv, 2024 pdf
• Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion
  Yingxuan Li, Ryota Hinami, Kiyoharu Aizawa, Yusuke Matsui
  arXiv, 2024 pdf
• Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval
  Ryoya Nara, Yu-Chieh Lin, Yuji Nozawa, Youyang Ng, Goh Itoh, Osamu Torii, Yusuke Matsui
  arXiv, 2024 pdf
• PCF Learned Sort: a Learning Augmented Sort Algorithm with O(nloglogn) Expected Complexity
  Atsuki Sato, Yusuke Matsui
  arXiv, 2024 pdf
• High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis
  Takuto Onikubo, Yusuke Matsui
  arXiv, 2024 pdf
• Broadcast Product: Shape-aligned Element-wise Multiplication and Beyond
  Yusuke Matsui, Tatsuya Yokota
  arXiv, 2024 project pdf
• Fast Construction of Partitioned Learned Bloom Filter with Theoretical Guarantees
  Atsuki Sato, Yusuke Matsui
  arXiv, 2024 pdf
• FlexFlood: Efficiently Updatable Learned Multi-dimensional Index
  Fuma Hidaka, Yusuke Matsui
  arXiv, 2024 pdf
• Defense-Prefix for Preventing Typographic Attacks on CLIP
  Hiroki Azuma, Yusuke Matsui
  arXiv, 2023 pdf
• Fast Partitioned Learned Bloom Filter
  Atsuki Sato, Yusuke Matsui
  arXiv, 2023 pdf
• General and Practical Tuning Method for Off-the-Shelf Graph-Based Index: SISAP Indexing Challenge Report by Team Utokyo
  Yutaro Oguri, Yusuke Matsui
  arXiv, 2023 pdf
• Manga109Dialog A Large-scale Dialogue Dataset for Comics Speaker Detection
  Yingxuan Li, Kiyoharu Aizawa, Yusuke Matsui
  arXiv, 2023 pdf
• Relative NN-Descent: A Fast Index Construction for Graph-Based Approximate Nearest Neighbor Search
  Naoki Ono, Yusuke Matsui
  arXiv, 2023 pdf
• Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights
  Ryoya Nara, Yusuke Matsui
  arXiv, 2023 pdf
• ARM 4-bit PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM
  Yusuke Matsui, Yoshiki Imaizumi, Naoya Miyamoto, Naoki Yoshifuji
  arXiv, 2022 pdf
• Unbiased Scene Graph Generation using Predicate Similarities
  Misaki Ohashi, Yusuke Matsui
  arXiv, 2022 pdf
• Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations
  Yasunori Kudo, Keisuke Ogaki, Yusuke Matsui, Yuri Odagiri
  arXiv, 2018 project
• Object Detection for Comics using Manga109 Annotations
  Toru Ogawa, Atsushi Otsubo, Rei Narita, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  arXiv, 2018 project
• PQTable: Non-exhaustive Fast Search for Product-quantized Codes using Hash Tables
  Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  arXiv, 2017 project
• PQk-means: Billion-scale Clustering for Product-quantized Codes
  Yusuke Matsui, Keisuke Ogaki, Kiyoharu Aizawa, Toshihiko Yamasaki
  arXiv, 2017 project
• Sketch-based Manga Retrieval using Manga109 Dataset
  Yusuke Matsui, Kota Ito, Yuji Aramaki, Toshihiko Yamasaki, Kiyoharu Aizawa
  arXiv, 2015 project

Tutorial

• Neural Search in Action
  Yusuke Matsui, Martin Aumüller, Han Xiao
  CVPR 2023 Tutorial, 2023 link
• Effective and Efficient: Toward Open-world Instance Re-identification
  Zheng Wang, Wu Liu, Yusuke Matsui, Shin'ichi Satoh
  ACMMM 2020 Tutorial, 2020 link
• Image Retrieval in the Wild
  Yusuke Matsui, Takuma Yamaguchi, Zheng Wang
  CVPR 2020 Tutorial, 2020 link

• 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)