I am Head of the ArtificiaI Intelligence (AI) Research team at Fieldbox. This company builds, deploys and maitains AI soltuions for industrial clients worldwide.
I have a background in applied Mathematics. I defended my PhD at Télécom Paris, in the image processing team of the LTCI, in June 2016. The topic of my thesis deals with the elaboration of new models for the restoration and the interpretation of satellite SAR (Synthetic Aperture Radar) images.
During my post-doc at Université de Caen in the Image team of the GREYC, I worked on graph signal processing in collaboration with Julien Rabin and Abderrahim Elmoataz. I was involved in the GRAPHSIP and NUMNIE projects.
My main research interests in random order are:
-
- Image processing and computer vision (denoising, classification, segmentation, feature matching, object detection, OCR, depth estimation…)
- Patch-based dictionary learning
- Gaussian mixture models
- Signal processing on graphs with variational approaches
- Predictive models for time series and tabular data
- Deep learning: Variational Auto-encoders for industiral data, Self Supervised Learning, Vision Transformers, Interpretability
- Data: SAR images, natural images, 3D point clouds, time series, tabular data…