Riwal LEFORT, postdoc

RESEARCH INTERESTs

• Data analysis (modeling, interpretation, dynamics)
  

• Data processing

• Machine learning with complex data (active learning, supervised learning, weakly supervised learning, semi-supervised learning, unsupervised learning)

• image and video processing

• Computer science

• Computer vision (spatial statistics, spatio-temporal features (SIFT, HOG, etc))

• Biological applications

• Data Indexation

PROJECTS

• Cell biology: In collaboration with biologists from Basel and Geneva, and with CvLAB at EPFL, we are investigating the prediction of morphodynamical properties of neurons in videos from gene expression.

• Fisheries acoustics: In collaboration with Telecom Bretagne and the French Research Institute for Exploration of the Sea (IFREMER), we are investigating the fish school recognition in acoustic images.

PUBLICATIONS

Book chapter:

• R. Lefort, R. Fablet, J-M. Boucher, "Weakly supervised learning: application to fish school recognition", in the book "New Advances in Intelligent Signal Processing", Springer, on the accasion of the ten years existence of the IEEE WISP series, 203-223, 2011.

Journal papers:

• R. Lefort, R. Fablet, L. Berger, J-M. Boucher, "Spatial statistcs of objects in 3D sonar images: Application to fisheries acoustics", Geosciences and Remote Sensing Letters, 2012, 9(1), 56-59.

• R. Lefort, R. Fablet, J-M. Boucher, "Object recognition using proportion-based prior information: application to fisheries acoustics", Pattern Recognition Letters, 2011, 32(2), 153-158.

• R. Lefort, R. Fablet, J-M. Boucher, "Classification faiblement supervisée : arbre de décision probabiliste et apprentissage itératif", numéro spécial RNTI : Fouille de données complexes "Complexité liées aux données multiples". To appear.

• R. Fablet, R. Lefort, I. Karoui, J. Masse, J-M. Boucher, C. Scalabrin, L. Berger, "Classifying fish schools and estimating their species proportions in fishery-acoustic surveys", ICES journal of marine science, 2009, 66(6), 1136-1142.

Conferences:

• R. Lefort, F. Fleuret, "A tree-based distance between distributions: application to classification of neurons", ICASSP 2012 : IEEE International Conference on Acoustics, Speech and Signal Processing, march. 2012, Kyoto, Japan.
• R. Lefort, L. Fusco, F. Benmansour, K. Smith, O. Pertz, F. Fleuret, "Machine learning techniques to analyse complex, computer vision-extracted, dynamic cellular phenotypes", 1st International SystemsX.ch Conference on Systems Biology, oct. 2011, Basel, Switzerland.
• G. Gonzalez, L. Fusco, R. Lefort, F. Benmansour, P. Fua, K. Smith, "Automated Quantification of Morphodynamics for High-Throughput Live Cell Imaging Datasets", 1st International SystemsX.ch Conference on Systems Biology, oct. 2011, Basel, Switzerland.
• L.M. Fusco, K. Smith, F. Benmansour, R. Lefort, F. Fleuret, P. Fua, O. Pertz, "Morphodynamic profiling to explore spatio-temporal signaling networks regulating neurite outgrowth", 1st International SystemsX.ch Conference on Systems Biology, oct. 2011, Basel, Switzerland.
• R. Lefort, R. Fablet, J-M. Boucher, "Weakly supervised learning", CLADAG 2011, 8th scientific meeting of the CLassification and Data Analysis Group of the Italian Statistical Society, sept. 2011, Pavia, Italia.
• R. Lefort, R. Fablet, J-M. Boucher, "Apprentissage itératif pour une connaissance a priori des labels", EGC 2011 : 11ème Conférence Internationale Francophone sur l'Extraction et la Gestion des Connaissance, janv. 2011, Brest, France.

• R. Lefort, R. Fablet, J-M. Boucher, "Weakly supervised classification of objects in images using soft random forests", ECCV 2010 : European Conference on Computer Vision, sept. 2010, Heraklion, Crete, Greece.

• R. Lefort, R. Fablet, J-M. Boucher, "Weakly supervised learning with decision trees applied to fisheries acoustics", ICASSP 2010 : IEEE International Conference on Acoustics, Speech and Signal Processing, march 2010, Dallas, US.

• R. Lefort, R. Fablet, J-M. Boucher, "Méthodes d'apprentissage faiblement supervisé : arbres de décision et classification itérative", RFIA 2010 : 17ème congrès AFRIF-AFIA en Reconnaissance des Formes et Intelligence Artificielle, janv. 2010, Caen, France.

• R. Lefort, R. Fablet, I. Karoui, J-M. Boucher, "Combining image-level and object-level inference for weakly supervised object recognition. Application to fisheries acoustics", ICIP 2009 : IEEE International Conference on Image Processing, nov. 2009, Cairo, Egypt.

• R. Lefort, R. Fablet, J-M. Boucher, "Weakly supervised classification with bagging in fisheries acoustics", WISP 2009 : IEEE International symposium on Intelligent Signal Processing, august 2009, Budapest, Hungary

• R. Lefort, R. Fablet, J-M. Boucher, "Classification et apprentissage faiblement supervisé en acoustique halieutique", GRETSI 2009 : XXIIe colloque du Groupe de Recherche et d'Etudes du Traitement du Signal, sept. 2009, Dijon, France.

• R. Fablet, R. Lefort, C. Scalabrin, J. Masse, J-M. Boucher, "Weakly supervised learning using proportion-based information : an application to fisheries acoustics", ICPR 2008 : 19th international conference on Pattern Recognition, dec. 2008, Tampa, USA.

• R. Lefort, R. Fablet, J-M. Boucher, S. Bourguignon, L. Berger, "Automatic fish school classification for acoustic sensing of marine ecosystems", Oceans 2008, MTS/IEEE, sept. 2008, Quebec, Canada.

• R. Lefort, M. Résibois, C. Person, H. Lattard, G. Guevel, M. Le Hénaff, Y. Toutain, "Etude d'un dosimètre portatif pour les études épidémiologiques", 1ères rencontres scientifiques de la Fondation Santé et Radiofréquences, oct. 2007, Paris, France.