Keynote speakers

David Picard

Senior Research Scientist at IMAGINE, École des Ponts ParisTech, France.

David Picard received  the  M.Sc.  in  Electrical Engineering  in  2005  and  the  Ph.D.  in  Image and  Signal  Processing  in  2008.  He  joined  the ETIS laboratory at the ENSEA Graduate School (France) in 2010 as associate professor. Since september 2019 he is a senior Research Scientist at the Ecole des Ponts ParisTech (ENPC). His research interests include image processing and machine learning for visual information processing, with focus on kernel methods, deep learning and distributed learning systems.

Website: https://davidpicard.github.io/

Title: Image Similarity: from Matching Kernels to Deep Metric Learning

Being able to define a similarity between images is a key task in computer vision as it is a necessary step to solve many popular problems such as image retrieval, automatic labeling, segmentation, etc. A historic approach inspired by stereo-analysis consists in counting the number of nearly identical regions of interest between two images. However, this approach is not compatible with machine learning tools and has to be adapted using what is known as matching kernels. In this talk, we show examples of these matching kernels and how their linearization leads to powerful representation learning techniques. We draw a parallel between these approaches and recent deep metric learning developments and we show that both are trying to solve a similar problem of distribution matching. We finally show how to tackle this distribution matching problem in deep metric learning by introducing a high order moment based regularization criterion.

Hedi Tabia

Professor at Université d'Évry, Université Paris Saclay, France. 

Hedi Tabia obtained the Phd degree in computer science from the University of Lille in 2011. From october 2011 to august 2012, he held a postdoctoral research associate position at the IEF laboratory (University of Paris-sud). During 2012-2019, he was an associate professor at the ENSEA. Since september 2019 he is a professor at Université d'Évry (Université Paris Saclay). His research interests include various domains of Machine Learning, Computer Vision and Computer Graphics.

 Website: https://perso-etis.ensea.fr/tabia/

Title: 3D data Analysis

This talk reviews the main results of our research activities carried out over the last few years. During this period, we have been particularly active in developing mathematical tools to describe, recognize, retrieve, and classify three dimensional (3D) Data. These are fundamental problems and building blocks to many applications in computer vision, computer graphics, medical imaging, and archeaology. The presented contributions goes around three main issues; namely 3D shape analysis, cross domain retrieval, and 3D action recognition.