Guillaume Charpiat's HomePage
TAU Team - INRIA Saclay
Address: Office 2054, Claude Shannon bldg (a.k.a. 660, "Digitéo"), Orsay, France
Phone: (+33)1 69 15 39 91
en français ?
Since 2015 I've been a researcher in the
TAO/TAU team (machine learning and optimisation), at INRIA Saclay.
Bio: I defended my PhD thesis in computer vision within the Odyssee Team in December 2006;
my advisors were Olivier Faugeras and Renaud Keriven. Then I spent one year as a post-doc at the Max Planck Institute for Biological Cybernetics in Bernhard Schölkopf's team (statistical learning). In 2008 I joined the Pulsar/St☆rs team (video understanding), at INRIA Sophia-Antipolis, and in 2015 the TAO/TAU team (machine learning and optimisation), at INRIA Saclay.
CV and keywords
I have a special page to present , check the nice pictures! my work with images and videos
Job offers :
No "short summer internship" available for foreign students (administratively too complex).
My resume (not really interested in job offers, but open to consulting).
My works/fields-of-interest in a few key-words:
Cf my PhD students' topics
Machine learning theory for neural networks: architecture self-adaptation, guaranties (in some cases), learning PDEs and numerical simulations
Main applications: satellite imagery, peoples' genetics, protein conformation... and also: weather forecast, brain imagery, etc.
Statistical learning, "artificial intelligence"
Unify statistical learning and "logical" models (e.g.: learn grammar, detect an algebric group operator)
How to learn possibly everything, without imposing any predefined structure ?
Image / video segmentation
Shapes (object boundaries)
Structure of the space of shapes
Metrics (distance between shapes, cost of deformations), shape matching (point-to-point)
Learning functions from/to the space of shapes
Learning how to predict an image given another one with different modality
Automatic image colorization (color from greyscale texture)
Prediction CT images (computed tomography) from MR scans (magnetic resonnance)
Tools used: kernel methods, graph-cuts
Aim: shape priors for image segmentation
Method: mean and statistics of images, of curves (and more generally surfaces)
Tools: non-rigid registration, shape gradient (choice of an inner product to perform gradient descents)
Energies, metrics considered: Hausdorff distance, geodesics, local cross-correlation.
Publications: (first author is underlined when not me)
(I also have a special webpage dedicated to present my publications, ) with images and videos
Chapter , with Ilja Bezrukov, Yasemin Altun, Matthias Hofmann and Bernhard Schölkopf, chapter of the book Machine Learning Methods for Automatic Image Colorization , R. Lukac Editor, CRC Press, to appear soon. Computational Photography: Methods and Applications [ bibtex][ new results]
Chapter , with Matthias Hofmann and Bernhard Schölkopf, chapter of the book Kernel methods in medical imaging , N. Paragios, J. Duncan & N. Ayache Editors, Springer, 2008. Biomedical Image Analysis: Methodologies and Applications [ bibtex]
Chapter , with Olivier Faugeras, Renaud
Keriven and Pierre Maurel, chapter of the book Approximations of shape metrics and application to shape
warping and empirical shape statistics , H. Krim & A. Yezzi Editors, Birkaüser 2006. Statistics and
Analysis of Shapes [ bibtex]
International Journals with Reviewing Board:
, with High-Resolution Aerial Image Labeling With Convolutional Neural Networks Emmanuel Maggiori, Yuliya Tarabalka and Pierre Alliez, dans Transactions on Geoscience and Remote Sensing, TGRS 2017. [ local copy] [ bibtex]
, with (Learning Iterative Processes with) Recurrent Neural Networks to Correct Satellite Image Classification Maps Emmanuel Maggiori, Yuliya Tarabalka and Pierre Alliez, in Transactions on Geoscience and Remote Sensing, TGRS 2016. [ local copy] [ bibtex]
, with Giacomo Nardi, Gabriel Peyré and François-Xavier Vialard, in Finsler Steepest Descent with Applications to Piecewise-regular Curve Evolution Interfaces and Free Boundaries, IFB 2016. [ local copy] [ bibtex]
, with Convolutional Neural Networks for Large-Scale Remote Sensing Image Classification Emmanuel Maggiori, Yuliya Tarabalka and Pierre Alliez, in Transactions on Geoscience and Remote Sensing, TGRS 2016. [ local copy] [ bibtex]
, with Spatio-Temporal Video Segmentation with Shape Growth or Shrinkage Constraint Yuliya Tarabalka, Ludovic Brucker and Björn H. Menze, in Transactions on Image Processing, TIP 2014. [ local copy] [ bibtex]
, with Multiple Birth and Cut Algorithm for Multiple Object Detection , Xavier Descombes and Josiane Zerubia, in the Ahmed Gamal Eldin Journal of Multimedia Processing and Technologies, JMPT 2011. [ bibtex]
, with MRI-Based Attenuation Correction for PET/MRI: A Novel Approach Combining Pattern Recognition and Atlas Registration Matthias Hofmann, Florian Steinke, Verena Scheel, Jason Farquhar, Philip Aschoff, Michael Brady, Bernhard Schölkopf and Bernd J. Pichler, in the Journal of Nuclear Medicine, Volume 49, Number 11, November 2008, JNM 2008. [ bibtex]
, with Pierre Maurel, Jean-Philippe Pons, Renaud
Keriven and Olivier Faugeras, in the Generalized Gradients: Priors on
Minimization Flows International Journal of Computer Vision, Volume 73, Number 3, July 2007, IJCV 2007. [ bibtex]
, with Olivier Faugeras and Renaud Keriven,
in the journal Approximations of Shape Metrics and Application to Shape Warping and
Empirical Shape Statistics Foundations of Computational Mathematics,
FoCM 2004. [ bibtex]
Other International Journals:
, with Variational, geometric, and statistical methods for modeling brain anatomy
and function Olivier Faugeras, Geoffray Adde,
Christophe Chefd'Hotel, Maureen Clerc, Thomas Deneux, Rachid Deriche,
Gerardo Hermosillo, Renaud Keriven, Pierre Kornprobst, Jan Kybic,
Christophe Lenglet, Lucero Lopez-Perez, Théo Papadopoulo, Jean-Philippe
Pons, Florent Ségonne, Bertrand Thirion, David Tschumperlé, Thierry
Viéville and Nicolas Wotawa, in the journal ,
23S1:S46-S55, 2004. Note: Special issue: Mathematics in Brain Imaging -
Edited by P.M. Thompson, M.I. Miller, T. Ratnanather, R.A. Poldrack and T.E. Nichols.
Pre-prints (submitted to journals/conferences or about to be):
International Conferences with Reviewing Board:
with Deep Learning for Hurricane Track Forecasting from Aligned Spatio-temporal Climate Datasets Sophie Giffard-Roisin, Mo Yang, Balázs Kégl and Claire Monteleoni,
Modeling and decision-making in the spatiotemporal domain workhop at NIPS 2018.
local copy] [ bibtex]
Aligning and Updating Cadaster Maps with Aerial Images by Multi-Task, Multi-Resolution Deep Learning
Nicolas Girard and Yuliya Tarabalka,
Asian Conference on Computer Vision ACCV 2018.
source code] [ local copy] [ bibtex]
with Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing Armand Zampieri, Nicolas Girard and Yuliya Tarabalka,
European Conference on Computer Vision ECCV 2018.
[ local copy] [ bibtex]
with The 2018 Climate Informatics Hackathon: Hurricane Intensity Forecast Sophie Giffard-Roisin, David Gagne, Alexandre Boucaud, Balázs Kégl, Mo Yang and Claire Monteleoni,
Climate Informatics CI 2018.
[ local copy] [ bibtex] [ challenge and associated code]
with Fused Deep Learning for Hurricane Track Forecast from Reanalysis Data Sophie Giffard-Roisin, Mo Yang, Balázs Kégl and Claire Monteleoni,
Climate Informatics CI 2018.
local copy] [ bibtex]
with Optimizing deep video representation to match brain activity Hugo Richard, Ana Luisa Pinho and Bertrand Thirion,
Conference on Cognitive Computational Neuroscience CCN 2018.
local copy] [ bibtex]
with Polygonization of remote sensing classification maps by mesh approximation Emmanuel Maggiori, Yuliya Tarabalka and Pierre Alliez,
International Conference on Image Processing ICIP 2017.
[ local copy] [ bibtex]
with High-resolution image classification with convolutional networks Emmanuel Maggiori, Yuliya Tarabalka and Pierre Alliez,
International Geoscience and Remote Sensing Symposium IGARSS 2017.
with Can semantic labeling methods generalize to any city? The Inria aerial image labeling benchmark Emmanuel Maggiori, Yuliya Tarabalka and Pierre Alliez,
International Geoscience and Remote Sensing Symposium IGARSS 2017.
local copy] [ benchmark] [ bibtex]
with Fully Convolutional Neural Networks For Remote Sensing Image Classification Emmanuel Maggiori, Yuliya Tarabalka and Pierre Alliez,
International Geoscience and Remote Sensing Symposium IGARSS 2016. [ bibtex]
, with A Nonparametric Model for Brain Tumor Segmentation and Volumetry in Longitudinal MR Sequences Esther Alberts, Yuliya Tarabalka, Thomas Huber, Marc-André Weber, Jan Bauer, Claus Zimmer and Björn H. Menze, Brain Lesions workshop, held at the International Conference on Medical Image Computing and Computer Assisted Intervention MICCAI BrainLes 2015. [ bibtex]
, with Optimizing Partition Trees for Multi-object Segmentation with Shape Prior Emmanuel Maggiori and Yuliya Tarabalka, British Machine Vision Conference BMVC 2015. [ bibtex]
, with Improved partition trees for multi-class segmentation of remote sensing images Emmanuel Maggiori and Yuliya Tarabalka, International Geoscience and Remote Sensing Symposium IGARSS 2015. [ bibtex]
, with Multiple Object Tracking by Efficient Graph Partitioning Ratnesh Kumar and Monique Thonnat, Asian Conference on Computer Vision ACCV 2014. [ bibtex]
, with Hierarchical Representation of Videos with Spatio-Temporal Fibers Ratnesh Kumar and Monique Thonnat, Winter Conference on Applications of Computer Vision WACV 2014. [ local copy] [ bibtex]
, with Enforcing Monotonous Shape Growth or Shrinkage in Video Segmentation Yuliya Tarabalka, Ludovic Brucker and Björn H. Menze, British Machine Vision Conference BMVC 2013. [ bibtex][ C++ code]
, with An Efficient Optimizer for Simple Point Process Models Ahmed Gamal Eldin, Xavier Descombes and Josiane Zerubia, SPIE Computational Imaging XI, 2013. [ bibtex]
, with A Graph-Cut-based Method for Spatio-Temporal Segmentation of Fire from Satellite Observations Yuliya Tarabalka, International Geoscience and Remote Sensing Symposium IGARSS 2013. [ bibtex]
, with Learning to Match Appearances by Correlations in a Covariance Metric Space Slawomir Bak, Etienne Corvée, François Brémond and Monique Thonnat, European Conference on Computer Vision ECCV 2012.
, with A Cognitive Vision System for Nuclear Fusion Device Monitoring Vincent Martin, Victor Moncada, Jean-Marcel Travere, Thierry Loarer, François Bremond and Monique Thonnat, International Conference on Computer Vision Systems ICVS 2011.
, with A Fast Multiple Birth and Cut Algorithm using Belief Propagation , Xavier Descombes and Josiane Zerubia, Ahmed Gamal Eldin International Conference on Image Processing ICIP 2011.
, Exhaustive Family of Energies Minimizable Exactly by a Graph Cut Computer Vision and Pattern Recognition CVPR 2011.
[ bibtex][ C++ code]
, with Converting Level Set Gradients to Shape Gradients Siqi Chen and Richard J. Radke, European Conference on Computer Vision ECCV 2010. [ bibtex][ movies]
, Learning Shape Metrics based on Deformations and Transport Second Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment NORDIA 2009, workshop of ICCV 2009. [ bibtex][ suppl.mat.][ poster]
, with Matthias Hofmann and Bernhard Schölkopf, Automatic Image Colorization via Multimodal Predictions European Conference on Computer Vision ECCV 2008. [ bibtex][ Linux.exec.code]
, with MR-Based PET Attenuation Correction: Method and Validation Matthias Hofmann, Florian Steinke, Verena Scheel, Mike Brady, Bernhard Schölkopf and Bernd Pichler, IEEE Nuclear Science Symposium and Medical Imaging Conference NSS-MIC 2007. [ bibtex]
, with Renaud Keriven and Olivier Faugeras,
Shape Statistics for Image Segmentation with prior Conference on Computer Vision and Pattern Recognition CVPR 2007. [ bibtex]
, with Jean-Philippe Pons, Renaud Keriven and
Designing Spatially Coherent
Minimizing Flows for Variational Problems Based on Active
Contours International Conference on Computer Vision ICCV 2005. [ bibtex]
, with Olivier
Faugeras and Renaud Keriven, Image Statistics based on Diffeomorphic Matching International Conference on Computer
Vision ICCV 2005 [. bibtex] (with a facial expression recognition task, joint work with Jean-Yves Audibert). More complete version here
, with Olivier Faugeras
and Renaud Keriven, Shape Metrics, Warping and Statistics Proceedings of the International
Conference on Image Processing, ICIP 2003. IEEE Signal Processing Society. [ bibtex]
Other International Conferences:
, with Pierre Maurel, Renaud Keriven et Olivier
Faugeras, Distance-Based Shape
Statistics IEEE International Conference on Acoustics, Speech, and
Signal Processing, Special Session: Statistical
Inferences on Nonlinear Manifolds with Applications in Signal and Image
Processing (This article mainly summarizes some previous articles but also
briefly introduces the . graph Laplacian applied to shapes) ICASSP 2006. [ bibtex]
Poster at the (september 2003)
Category-Level 3D Object Recognition Systems: An International Workshop
Talks and Posters: (not often updated)
Miscellaneous animations (image segmentation with/without shape prior;
evolution obtained by gradient descent with the standard inner product vs
one which favors rigid transformations; first modes of deformations of a
database of faces) presented in my PhD defense.
Faces: characteristical modes associated to a face
database (intensity variations and warping at the same time)
I have a special page to present , check it!
my work with images and videos
Current and former students:
Julien Girard (formal proof of neural networks), co-supervised with Zakaria Chihani and Marc Schoenauer [2018-]
Loris Felardos (neural networks for molecual dynamics simulation), co-supervised with Jérôme Hénin and Bruno Raffin [2018-]
Nicolas Girard (satellite image vectorization using neural networks), co-supervised with Yuliya Tarabalka and Pierre Alliez [2017-]
Théophile Sanchez (flexibility of neural networks with application to peoples' genetics), co-supervised with Flora Jay and Marc Schoenauer [2017-]
Pierre Wolinski (learning the structure of neural networks), co-supervised with Yann Ollivier [2016-]
Emmanuel Maggiori (segmentation of satellite images with shape prior), co-supervised with Yuliya Tarabalka and Pierre Alliez [2015-2017]
Ratnesh Kumar (fiber-based segmentation of videos for activity recognition), co-supervised with Monique Thonnat [2011-2014]
Master 2 students
Andrew Khalel (pan-sharpening using neural networks (fusion of images of different resolutions and modalities)), co-supervised with Yuliya Tarabalka 
Mo Yang (weather forecast: prediction of the trajectory of storms), co-supervised with Claire Monteleoni and Sophie Giffard-Roisin 
Hugo Richard (video generation and analysis, with neural networks, with application to brain imaging), co-supervised with Bertand Thirion [2017-2018]
Armand Zampieri (registration of satellite images with the cadastre), co-supervised with Yuliya Tarabalka 
Théophile Sanchez (peoples' genetics), co-supervised with Flora Jay 
Priyanka Mandikal (registration of 3D medical images), collaboration with Therapixel 
Emmanuel Maggiori (shape features in partition trees of images), co-supervised with Yuliya Tarabalka 
Kandan Ramakrishnan (tracking dust particles in a fusion reactor), co-supervised with Vincent Martin 
Ezequiel Cura (strategies for automatic model construction) 
Anja Schnaars (texture-based segmentation) 
Master 1 students, L3 students or equivalent
Martin Toth (explanation of the decision taken by a neural network), collaboration with Hossein Khonsari [2017-2019]
Louis Bethune (tracking paramecia with a motorized microscope using reinforcement learning), collaboration with Romain Brette 
Raphaël Guegan (crowd dynamics estimation with neural networks), co-supervised with Emanuel Aldea 
Etienne Desbois (skin disease classification), collaboration with Hossein Khonsari 
Sorana Capalnean (classification of gestures obtained by a depth camera) 
Bertrand Simon (dynamics of an articulated movement and gesture recognition) 
Raphaël Jaiswal (driving scenario classification), collaboration with Renault [2017-2018]
Etienne Brame (multi-class classification of a big database of images), collaboration with Armadillo within the Adamme project [2017-2018]