People

Matthijs Douze

Research Scientist

I am a research scientist at the Facebook AI Research (FAIR) lab in Paris since November 2015. At Facebook I am working on large-scale indexing (see the Faiss library), machine learning with graphs and similarity search on images and videos. I obtained a master’s degree from the ENSEEIHT engineering school and defended my PhD at University of Toulouse in 2004. In 2005-2015 I joined the LEAR team at INRIA Grenoble where I worked on a variety of topics, including image indexing, large-scale vector indexing, event recognition in videos and similar video search. In 2010-2015 I also managed Kinovis, a large 3D motion capture studio at INRIA and developed high-performance geometric algorithms for constructive solid geometry operations.

In addition to FAIR’s general research topics, I am interested in snappy algorithms that process images and produce graphical results.

Interests

Computer vision, machine learning, similarity search and large-scale indexing

Latest Publications

Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition

Adrien Dufraux, Emmanuel Vincent, Awni Hannun, Armelle Brun, Matthijs Douze

ASRU - December 13, 2019

Fixing the train-test resolution discrepancy

Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou

NeurIPS - December 9, 2019

Deep Clustering for Unsupervised Learning of Visual Features

Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze

ECCV 2018 - September 9, 2018

LAMV: Learning to align and match videos with kernelized temporal layers

Lorenzo Baraldi, Matthijs Douze, Rita Cucchiara, Hervé Jégou

CVPR 2018 - June 19, 2018

Link and code: Fast indexing with graphs and compact regression codes

Matthijs Douze, Alexandre Sablayrolles, Hervé Jégou

CVPR 2018 - June 19, 2018

Low-shot learning with large-scale diffusion

Matthijs Douze, Arthur Szlam, Bharath Hariharan, Hervé Jégou

CVPR 2018 - June 18, 2018

Learning Multilingual Joint Sentence Embeddings with Neural Machine Translation

Holger Schwenk, Matthijs Douze

ACL Workshop on Representation Learning for NLP - July 31, 2017

Polysemous Codes

Matthijs Douze, Hervé Jégou, Florent Perronnin

ECCV - October 10, 2016