PamiTC Job Board - Posting Details

Title: PostDoc position on CNN approaches for face recognition, verification, and retrieval.Posted: December 5, 2014
Company/Institution: INRIA
Location: Grenoble, France
Department: LEAR Team


Postdoc position at INRIA
LEAR research group in Grenoble

Topic: CNN approaches for face verification and recognition in the wild

The topic of this postdoc position is to develop convolutional neural network (CNN) approaches for several tasks. These include face recognition, as well as face verification and retrieval. For these latter tasks the networks are used to learn metrics to compare faces that suppress nuisance factors such as pose, expression, lighting and viewpoint. The developed approaches will be evaluated on the most challenging public face recognition, verification, and retrieval datasets.

Your profile:
* PhD degree (preferably in Computer Vision or Machine Learning)
* Solid programming skills; the project involves programming in C and Python.
* Solid mathematics knowledge (especially linear algebra and machine learning)
* Creative and highly motivated
* Fluent in written and spoken English
* Prior knowledge on GPU CUDA programming is an asset

1 year, renewable.

Start date:
as soon as possible (posted December 2014).

The position is offered at the "Rhone-Alpes" Research Unit of INRIA, located near Grenoble and Lyon, in France. The Unit includes more than 600 people, within 26 research teams and 10 support services. Grenoble is a lively city which hosts many foreign students and researchers. Located in the heart of the French Alps its direct surroundings offer great outdoor recreation including skiing, cycling, and hiking. Paris can be reached from Grenoble in 3h by train.

Application Instructions: Contact:
Jakob Verbeek,

Please send applications via email, including:
* a complete CV
* topic of your PhD thesis, with a weblink to the manuscript
* the name and email address of two references (including your PhD thesis supervisor)