Please note the deadline for application has passed and this vacancy is no longer available

Visual and audiovisual human behaviour analysis for Human-Centered Intelligent HCI

Department of Computing

 

Fixed Term Appointment for up to 48 months

 

Salary: £24,570 - £31,240

 

Imperial College is ranked in the top five universities of the world, according to the 2007 Times Higher Education Supplement league tables.  

The Department of Computing is a leading department of Computer Science among the UK Universities. It has consistently been awarded the highest research rating (5*) in Research Assessment Exercises and was rated as "Excellent" in the previous national assessment of teaching quality.  

An exciting opportunity has arisen for one Research Assistant for the prestigious European Research Council Starting Grant funded project on human naturalistic behaviour analysis. The purpose of the project is to attempt to build automated tools for machine understanding of human interactive behaviour in naturalistic contexts including human-computer interaction context. The envisioned technology will be based on findings in cognitive sciences and it will represent a set of visual and audiovisual spatiotemporal methods for automatic analysis of human spontaneous (as opposed to posed and exaggerated) patterns of behavioural cues including head pose, facial expression, visual focus of attention, hands and body movements, and vocal outbursts like laughter. These tools will be used further to reason about users’ spontaneous expressions of confusion, distress, fatigue, and boredom, to which the users’ interface needs to adapt and respond.

Within the project, the applicant will be responsible for design and development of a software platform where the envisioned technology components could be integrated to represent a set of audiovisual tools for machine analysis of human naturalistic behaviour as set out above. This software platform will also form the basis for design and development of human-centered intelligent interfaces, capable of adapting to users’ mental states like fatigue or boredom. The applicant will be also responsible for design and development of a robust, (near) real-time tool for multimodal, spatio-temporal analysis of naturalistic expressions of confusion, distress, fatigue, and boredom in typical single-user office-based HCI scenarios. The relevant modalities include visual modality (facial actions, head gestures, and gaze direction), audio modality (vocal outbursts like laughter), and ‘tactile’ modality (keystrokes, mouse movements, etc.).

The project involves significant R&D challenges, and the end results will contribute to development of more natural user interfaces as well as to development of computer-based education and ambient intelligence technologies.

To apply for this position, you will need to have a Masters Degree in Engineering or Computer Science. You should have proven knowledge and track record in one or more of the following areas: development and integration of mid- and large-scale computer vision systems, computer vision and machine learning, particularly in human behaviour (e.g. facial expression) tracking and analysis, and real-time video analysis.

You must be fluent in spoken and written English, have excellent communication skills, and be able to organize your own work with minimal supervision and prioritize work to meet deadlines. Preference will be given to applicants with a proven research record in the relevant areas. The post is full time with a fixed contract of 4 years and is based at the South Kensington Campus. 

 

You will be part of the Intelligent Human Behaviour Understanding Group (iBUG), Visual Information Processing Research Section, within the Computing Department and based at the South Kensington campus. For further information on the group and related projects http://www.doc.ic.ac.uk/~maja/

 

Applications must include the following:-

  • A College application form, which can be obtained from http://www3.imperial.ac.uk/employment/applicationformchairreaderclinlecresearch
  • A full CV Including, University degrees and dates, past and present posts, list of publications

     

  • A 1 page research statement should be provided indicating what you see are interesting research issues relating to the above posts, why your expertise is relevant, and what are your future research plans

     

Applications should be sent to:-

 

Marina Hall

Department of Computing,

Imperial College London,

South Kensington Campus,

London, SW7 2AZ

 

Email: marina.hall@imperial.ac.uk quoting reference: ERCMP11.

 

Closing Date: 1st October 2008