[Imageworld] PhD Studentship: Semantic Distance Learning For
frederic.jurie at info.unicaen.fr
Sun Jan 18 21:36:05 CET 2009
PhD Studentship: Semantic Distance Learning For Face/Person Recognition
The Computer Vision group of the University of Caen (France) and the
LEAR group at INRIA Grenoble, Rhone-Alpes (France) are looking for a
PhD student. The candidate will be jointly supervised and
will spend time in both institutions (http://lear.inrialpes.fr/ ;
Face and person recognition is one of the important problems in
computer vision and is required for a large number of applications.
However, despite the effort of the community, face/person recognition
is still a challenging problem: the same person can look very
differently according to his posture or clothing, while the difference
between two different persons can be small.
The goal of this project is to develop algorithms for quickly browsing
huge collections of faces/persons. The key issue is to learn distance
functions from the training data, which embed semantic information. This
semantic information allows to select face/person features (clothing,
hair color, etc.) to explore the face database. This research will
build on the paper "Randomized Clustering Forests for Image
Classification", by F Moosmann, E Nowak and F Jurie, PAMI 2008.
As soon as possible.
The student will be located at the Computer Vision group at the
University of Caen, but will spend approximately a quarter of his
time at the INRIA Grenoble research center.
Prof. Frederic Jurie, frederic.jurie at unicaen.fr
Res. Dir. Cordelia Schmid, cordelia.schmid at inrialpes.fr
* Masters degree (preferably in Computer Science or Applied
Mathematics; Electrical Engineering will also be considered)
* Solid programming skills; the project involves programming in Matlab and
* Solid mathematics knowledge (especially linear algebra and statistics)
* Creative and highly motivated
* Fluent in English, both written and spoken
* Prior knowledge in the areas of computer vision, machine learning
or data mining is a plus (ideally a Master thesis in a related field)
Please send applications via email, including:
* a complete CV
* graduation marks as well as rank
* topic of your Master thesis
* the name and email address of three references (including your Master
* if you already have research experience, please include a publication
list and references
Applications should be sent to Frederic Jurie (frederic.jurie at unicaen.fr)
and Cordelia Schmid (cordelia.schmid at inrialpes.fr). Applicants can be asked
to do a short assignment in order to demonstrate their research abilities.
More information about the Imageworld