Hervé Jégou
homepage:http://people.rennes.inria.fr/Herve.Jegou/
search externally:   Google Scholar,   Springer,   CiteSeer,   Microsoft Academic Search,   Scirus ,   DBlife

Description

I am a researcher employed by INRIA, in the Texmex team headed by Patrick Gros. I am a former student of the Ecole Normale Superieure de Cachan, holding a M.S. (2002) and PhD (2005) from University of Rennes I. During my PhD, I worked on error-resilient compression and joint source channel coding, supervised by Christine Guillemot. After that, I turned out to Computer Vision and Pattern Recognition. I joined the LEAR group (INRIA Grenoble) as a permanent researcher in 2006, and moved to INRIA Rennes in 2009.

My work is mainly focused on computer vision, with most of my contributions focused on large scale indexing techniques (vectors/images/video). In particular, I proposed several compressed-domain search techniques that scale from millions to billions of vectors/images while being ressource-efficient (CPU+memory).


Lectures:

lecture
flag Aggregating local descriptors into a compact image representation
as author at  23rd IEEE Conference on Computer Vision and Pattern Recognition 2010 - San Francisco,
11081 views
  tutorial
flag Large-scale and larger-scale image search
as author at  British Machine Vision Conference (BMVC), Surrey 2012,
6515 views