Publications · research · teaching · software · resume (pdf) · glitches
I am heading a research group in machine learning at the Idiap research institute, and I am member of the École Polytechnique Fédérale de Lausanne faculty, both in Switzerland. I received the PhD degree in Mathematics from University of Paris VI in 2000 and the habilitation degree in Applied Mathematics from University of Paris XIII in 2006.
My research is mainly about machine learning and probabilistic models for computer vision. I am looking at how to use very large feature sets for scene analysis with Charles Dubout, and for action selection with Leonidas Lefakis, and how to improve interactive image retrieval systems with Nicolae Suditu. With Riwal Lefort, and groups from Basel, Geneva and EPFL, we are investigating the prediction of phenotypical properties of neurons from gene expression.
I am the coordinator of the European project MASH. Our objective is to design an open platform to build a complex machine-learning system. Anyone can submit image feature extractors, and they are automatically combined with machine learning algorithms to solve problems in computer vision and robotics. You can check a presentation of the project at the ML Summer School @Purdue, 2011.
My main ongoing collaborations are with the CVLab at EPFL on multi-camera tracking with Horesh Ben Shitrit and Pascal Fua, and with the CSEM on hand detection in industrial environment with Karim Ali and David Hasler.
Finally, I am working on object detection and the estimation of machine-learning performance for vision with Don Geman. We have developed the Synthetic Visual Reasoning Test, a series of two-class image classification problems, to compare humans and algorithms.
My research is supported in part by the Swiss National Science Foundation, by the 7th Research Framework Program of the European Commission, and by the Hasler Foundation.
F. Fleuret, T. Li, C. Dubout, E. K. Wampler, S. Yantis, and D. Geman. Comparing machines and humans on a visual categorization test. Proceedings of the National Academy of Sciences (PNAS), 108(43):17621-17625, 2011. bib · pdf
C. Dubout and F. Fleuret. Boosting with Maximum Adaptive Sampling. In Proceedings of the Neural Information Processing Systems Conference (NIPS), pages 1332-1340, 2011. bib · pdf
F. Fleuret, P. Abbet, C. Dubout, and L. Lefakis. The MASH project. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), pages 626-629, 2011. bib · pdf
N. Suditu and F. Fleuret. HEAT: Iterative Relevance Feedback with One Million Images. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 2118-2125, 2011. bib · pdf
K. Ali, F. Fleuret, D. Hasler, and P. Fua. A Real-Time Deformable Detector. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 34(2):225-239, 2012. bib · pdf
J. Berclaz, E. Turetken, F. Fleuret, and P. Fua. Multiple Object Tracking using K-Shortest Paths Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 33(9):1806-1819, 2011. bib · pdf
L. Lefakis and F. Fleuret. Joint Cascade Optimization Using A Product Of Boosted Classifiers. In Proceedings of the Neural Information Processing Systems Conference (NIPS), pages 1315-1323, 2010. bib · pdf
F. Fleuret and D. Geman. Stationary Features and Cat Detection. Journal of Machine Learning Research (JMLR), 9:2549-2578, 2008. bib · pdf