Fabrice Michel

Machine Learning and Computer Vision Research Scientist

Name Fabrice Michel
Age 31
Address Paris, France
Languages French, English
Email (Click Here...)

Download PDF resume

Fabrice Michel

I received my Ph.D. from the Department of Applied Mathematics, Ecole Centrale Paris in 2013 under the supervision of Prof Nikos Paragios. I am also an alumnus of École Nationale des Ponts et Chaussées (2004-2008) and École Normale Supérieure de Cachan (2007-2008).

Prior to my graduation, I started working (2012) in France as a Research Scientist for Dassault Systèmes. During my time in academic research, I published 4 papers in international conferences mainly focused on machine learning applications to medical image registration. My work is now focused on improving the state of the art industrial solutions in Machine Learning and Computer Vision, Strategic Auditing and Patent Publication. My current research interests focus on Machine Learning applications to Image Understanding, Activity Recognition, Multi-modal Data Fusion, and Sparse Learning.

Patent Application 2014 - US20140358475

Body Posture Tracking

Malika Boulkenafed and Fabrice Michel


PhD Thesis - October 2013

Multi-Modal Similarity Learning for 3D Deformable Registration of Medical Images

Fabrice Michel

[pdf] [BibTeX entry]

ISBI 2011

Boosted metric learning for 3D multi-modal deformable registration

Fabrice Michel, Michael Bronstein, Alex Bronstein and Nikos Paragios

[pdf] [BibTeX entry]

CVPR 2010

Data Fusion through Cross-modality Metric Learning using Similarity-Sensitive Hashing

Michael M. Bronstein, Alexander M. Bronstein, Fabrice Michel and Nikos Paragios

[pdf] [BibTeX entry]


3D knowledge-based segmentation using pose-invariant higher-order graphs

Chaohui Wang, Olivier Teboul, Fabrice Michel, Salma Essafi and Nikos Paragios

[pdf] [BibTeX entry]

ISBI 2010

Image transport regression using mixture of experts and discrete Markov random fields

Fabrice Michel and Nikos Paragios

[pdf] [BibTeX entry]

Patent 2008 - US8218909

System and method for geodesic image matching using edge points interpolation

Ali Khamene and Fabrice Michel