AVEC 2017 menu

PhD Position University of Nottingham in Automatic Facial Expression Recognition

The School of Computer Science (CS) at the University of Nottingham offers an exciting opportunity for a PhD studentship in the field of Automatic Human Behaviour Understanding, applying and developing Computer Vision and Machine Learning techniques to aid future Human Computer Interaction (HCI). The PhD post is intended to complement and extend the existing research expertise in the School and help stimulate interdisciplinary expertise.

Facial expression is one of the primary means to communicate between humans. Besides communicative functions, facial expression behaviour carries information about all kinds of phenomena, including personality, mood, intentions, power, and can even indicate certain medical conditions. These higher level interpretations of facial expressions require the analysis of longitudinal data of a person, which due to its large duration cannot be efficiently analysed using traditional appearance or shape descriptors. A successful applicant would have to refine existing tools that describe facial expression behaviour in a low-dimensional space, and investigate means to learn the temporal aspects of episodes of facial behaviour in order to automatically detect phenomena that are known to manifest themselves in facial expression data, and discover if there are unknown phenomena that influence facial expression behaviour.

The studentship will be based at the School of Computer Science at the University of Nottingham and will be supervised by Dr Michel Valstar (http://www.cs.nott.ac.uk/~mfv/). Information about the school and its research areas can be found at http://www.nottingham.ac.uk/computerscience/. Informal enquiries can be made by email to Dr Michel Valstar (michel.valstar@nottingham.ac.uk).

This studenthsip will be for a period of three and a half years and includes payment of fees at the UK/EU rate and a postgraduate stipend of £13,590 in year one with increments in line with Research Council Rates. The position is open to students of any nationality, but non-UK students will require additional funding to cover tuition fees, which is awarded by the University on a competitive basis.

Students should have a first class honours degree or equivalent (or a Masters’ Degree), in Computer Science, Mathematics, Physics, Electrical Engineering, Statistics or a related discipline, and must be able to demonstrate strong analytical skills, and programming skills in Matlab and/or C++. Background in visual information processing, machine learning or pattern recognition, and experience using relevant libraries (e.g., OpenCV) is also desirable.

Applications consisting of, a CV listing all publications, your representative publications in PDF format (e.g. a chapter of your final year dissertation, or a published conference/journal paper), 3 reference letters, and a statement of research interests and other supporting documents. Please note that instead of the ‘Research Proposal’ we request a ‘Statement of Research Interests’. Your Statement of Research Interest should answer two questions: (i) Why are you interested in the proposed area? (ii) What is your experience in the proposed area? Your statement should be brief: no more than 500 words or one side of A4 paper, should be emailed to: Dr Michael Valstar, email: michel.valstar@nottingham.ac.uk.

Closing date: Monday 13 February 2012

Application: see http://www.nottingham.ac.uk/jobs/currentvacancies/ref/SCI1105

Leave a Reply




You can use these HTML tags

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>