The School of Computing is seeking to recruit a PhD researcher to work on multimedia content search to develop techniques to support new ways to search massive video and multimedia archives, which could revolutionise how users discover content in resources such as BBC Archives or YouTube. This PhD project is part of a large EPSRC funded research project, called MVSE (Content-based Multimodal Video Search by Examples), which includes researchers from Ulster University, University of Surrey, University of Cambridge and the BBC, who have come together to develop new technologies to enable users to search efficiently and accurately for relevant content in multimedia archives.
The MVSE project will use AI to interrogate all aspects of the multimedia content. For example, computer vision with deep learning will be used to interrogate each frame in a video for object identification and for face-based person identification; audio processing will be used for topic and context identification, as well as speaker identification. Using examples from each modality (visual, audio, text etc.), the system will provide multiple modality-specific content lists (each can be ranked by relevance in accordance to the knowledge descriptors for that modality).
Depending on the candidate’s interests and skills, this particular PhD will focus on (1) the user experience aspects (Human-AI interaction) of the advanced search interfaces or on (2) content ranking and fusing different content sets together for presentation to the end-user.
For option (1), this PhD project will investigate how to optimise the human-search interaction. This will include taking into account the user’s preferences whilst searching and any interactions that the user has with advanced search queries or with the use of faceted search. The PhD project will also align to evolving principles in human-centred AI where the end-users are involved in the design of the search-user interfaces.
For option (2), this PhD project will investigate how to rank each of the modality specific content lists and how to fuse these together taking into consideration user preferences such as diversity, efficiently and effectively using AI techniques.
Eligibility:
Applicants must meet the UK residency requirements in order to be eligible to apply for this funded opportunity. This means that you must have been resident in the United Kingdom for the full three year period before the first day of the first academic year of the course.
Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.
We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.
In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University offers the following levels of support:
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).
This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.
Due consideration should be given to financing your studies. Further information on cost of living
Submission deadline
Friday 18 June 2021
12:00AM
Interview Date
2 July 2021
Preferred student start date
mid September 2021
Telephone
Contact by phone
Email
Contact by email