World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
46
Citations
25807
World Ranking
6632
National Ranking
2927

Overview

Matthijs Douze is affiliated with Facebook in the United States and focuses on research within the field of computer science. The primary area of study includes computer vision and pattern recognition, with significant contributions documented in related subfields such as artificial intelligence, signal processing, radiology, nuclear medicine and imaging, and electrical and electronic engineering.

Their published work spans advanced image and video retrieval techniques, domain adaptation and few-shot learning, multimodal machine learning applications, advanced steganography and watermarking techniques, human pose and action recognition, advanced neural network applications, and image retrieval and classification techniques.

Frequent coauthors collaborating with Matthijs Douze include Hervé Jeǵou, Hugo Touvron, Ed Pizzi, Alexandre Sablayrolles, and Pierre-Emmanuel Mazaré.

Key publication venues where their research has appeared include arXiv (Cornell University), the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE Transactions on Big Data, the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), and ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Selected recent papers authored or coauthored by Matthijs Douze are:

  • XCiT: Cross-Covariance Image Transformers, 2021, arXiv (Cornell University)
  • Training data-efficient image transformers & distillation through attention, 2020, arXiv (Cornell University)
  • Data Augmenting Contrastive Learning of Speech Representations in the Time Domain, 2020, arXiv (Cornell University)
  • LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference, 2021, arXiv (Cornell University)
  • THE FAISS LIBRARY, 2025, IEEE Transactions on Big Data

Best Publications

  • Product Quantization for Nearest Neighbor Search

    H Jégou;M Douze;C Schmid

  • Aggregating local descriptors into a compact image representation

    Herve Jegou;Matthijs Douze;Cordelia Schmid;Patrick Perez

  • Deep Clustering for Unsupervised Learning of Visual Features

    Mathilde Caron;Piotr Bojanowski;Armand Joulin;Matthijs Douze

  • Billion-Scale Similarity Search with GPUs

    Jeff Johnson;Matthijs Douze;Herve Jegou

  • Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search

    Herve Jegou;Matthijs Douze;Cordelia Schmid

  • Aggregating Local Image Descriptors into Compact Codes

    H. Jegou;F. Perronnin;M. Douze;J. Sanchez

  • Improving Bag-of-Features for Large Scale Image Search

    Hervé Jégou;Matthijs Douze;Cordelia Schmid

  • FastText.zip: Compressing text classification models

    Armand Joulin;Edouard Grave;Piotr Bojanowski;Matthijs Douze

  • Category-Specific Video Summarization

    Danila Potapov;Matthijs Douze;Zaid Harchaoui;Cordelia Schmid

  • On the burstiness of visual elements

    Herve Jegou;Matthijs Douze;Cordelia Schmid

  • Evaluation of GIST descriptors for web-scale image search

    Matthijs Douze;Hervé Jégou;Harsimrat Sandhawalia;Laurent Amsaleg

  • Training data-efficient image transformers & distillation through attention

    Hugo Touvron;Matthieu Cord;Matthijs Douze;Francisco Massa

  • Searching in one billion vectors: Re-rank with source coding

    Herve Jegou;Romain Tavenard;Matthijs Douze;Laurent Amsaleg

  • Combining attributes and Fisher vectors for efficient image retrieval

    Matthijs Douze;Arnau Ramisa;Cordelia Schmid

  • Packing bag-of-features

    Herve Jegou;Matthijs Douze;Cordelia Schmid

  • XCiT: Cross-Covariance Image Transformers.

    Alaaeldin El-Nouby;Hugo Touvron;Mathilde Caron;Piotr Bojanowski

  • An Image-Based Approach to Video Copy Detection With Spatio-Temporal Post-Filtering

    Matthijs Douze;Herve Jegou;Cordelia Schmid

  • Learning Joint Multilingual Sentence Representations with Neural Machine Translation

    Holger Schwenk;Matthijs Douze

  • Local Convolutional Features with Unsupervised Training for Image Retrieval

    Mattis Paulin;Matthijs Douze;Zaid Harchaoui;Julien Mairal

  • Fixing the train-test resolution discrepancy

    Hugo Touvron;Andrea Vedaldi;Matthijs Douze;Herve Jegou

Frequent Co-Authors

Hervé Jégou
Hervé Jégou Facebook (United States)
Cordelia Schmid
Cordelia Schmid French Institute for Research in Computer Science and Automation - INRIA
Zaid Harchaoui
Zaid Harchaoui University of Washington
Jakob Verbeek
Jakob Verbeek Facebook AI Research (FAIR) in Paris
Armand Joulin
Armand Joulin Google (United States)
Zeynep Akata
Zeynep Akata University of Tübingen
Noel E. O'Connor
Noel E. O'Connor Dublin City University
Andrew Zisserman
Andrew Zisserman University of Oxford
Piotr Bojanowski
Piotr Bojanowski Facebook (United States)
Lorenzo Torresani
Lorenzo Torresani Facebook (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online education options can open many doors for students interested in Computer Science and related fields. One popular choice is pursuing an online data science degree, which offers rigorous training in analytics, machine learning, and data management—highly in demand by leading tech employers.

If you're interested in applying technical skills in growing industries, the best 2 year construction management degree online can help you fast-track your career in project management and infrastructure technology.

Many computer science graduates look to advance their leadership and business expertise with online mba programs. These programs offer flexibility and often affordable options, blending strategic business knowledge with technical fluency.

For those seeking to specialize quickly, numerous online master's programs are available, allowing students to earn an advanced degree in just one year. These accelerated pathways can boost employability and career growth in dynamic fields related to computer science.

Best Scientists Citing Matthijs Douze

Trending Scientists

Recently Published Articles