Learning interactive avatars from digital media

Project description

Digital media such as TV shows, provide a rich resource for learning about human appearance and behaviour. This project will use recent ideas from machine learning to build an interactive avatar based on the characters appearing in TV shows. The avatar will look, sound and behave like the modelled character, interacting in a natural way, albeit without semantically meaningful content. The aim is to develop this realistic avatar as a baseline on which to build a future capability for meaningful discourse. In the longer term, we are interested in investigating applications in entertainment and interpersonal development, for example in helping people to learn a language.

Entry requirements

Applications are invited from candidates with a minimum of a UK upper second class honours degree (2:1), and/ or a Master's degree in a relevant subject. We also recognise relevant industrial and academic experience.

How to apply

Formal applications for research degree study should be made online through the university's website. Please state clearly in the research information section of your application, the name of the PhD you wish to apply for is 'Learning interactive avatars from digital media' as well as Professor David Hogg as your proposed supervisor. In the funding section, please state 'School of Computing Funded Studentships' as your sponsor.

If English is not your first language, you must provide evidence that you meet the University’s minimum English Language requirements.

We welcome scholarship applications from all suitably-qualified candidates, but UK black and minority ethnic (BME) researchers are currently under-represented in our Postgraduate Research community, and we would therefore particularly encourage applications from UK BME candidates.  All scholarships will be awarded on the basis of merit.

If you require any further information please contact the Graduate School Office
e: phd@engineering.leeds.ac.uk, t: +44 (0)113 343 8000.