Hervé Jégou (INRIA, France)
Topic: Very large-scale image and video retrieval
Hervé Jégou is a researcher employed by INRIA, in the TEXMEX team headed by Patrick Gros. He is a former student of the Ecole Normale Superieure de Cachan, holding a M.S. (2002) and PhD (2005) from University of Rennes I. During his PhD, he worked on error-resilient compression and joint source channel coding, supervised by Christine Guillemot. After that, he turned out to Computer Vision and Pattern Recognition. He joined the LEAR group (INRIA Grenoble) as a permanent researcher in 2006, and moved to INRIA Rennes in 2009. His work is mainly focused on large scale image/video/audio retrieval, and multi-dimensional indexing techniques. He has designed methods that scale from millions to billions of vectors/images while being ressource efficient (one machine, relatively low memory usage).