Queen’s University Belfast Featured PhD Programmes
University of Glasgow Featured PhD Programmes
University of Huddersfield Featured PhD Programmes
University of Liverpool Featured PhD Programmes
University College London Featured PhD Programmes

Object recognition regardless of Depiction

  • Full or part time
  • Application Deadline
    Monday, April 01, 2019
  • Competition Funded PhD Project (European/UK Students Only)
    Competition Funded PhD Project (European/UK Students Only)

Project Description

Object recognition is a well-established area of Visual Computing, with performance rates quoted well above 90%. However, all algorithms to date train and text almost exclusively on photographs; all, including neural architectures, suffer a significant fall in performance when artwork in included [1]. A solution requires research that addresses basic assumptions made by the current literature, in particular visual appearance is not sufficient [2].

A solution will require novelties that not only advance recognition but will underpin improvements in other areas of Visual Computing such as Style Transfer. A solution to this problem will also support applications in areas as diverse as Games manufacture, Graphic Design, Product protection, Art History and Accessible Computing. Example one: graphic designers wish to build tools for highly advanced image editing, not just photographs but artwork of all kinds. Example two: Art Historians wish to trace objects as they appear over different centuries in different parts of the world. Example three: phones that describe images, including artwork, help the visually impaired community gain access to visual content in their everyday lives. Recognition regardless of depiction is the essential key ingredient in all of these cases.

The successful candidate will design, develop, and demonstrate new neural networks that address this “cross depiction” problem in a general and principled manner. The candidate will be free to negotiate the exact trajectory of their line of work with the supervisor. There will be the opportunity to work with industrial partners in the Creative Sector, with the charitable sector, or with academics in other fields to apply basic research.

The successful applicant will be able to demonstrate an excellent academic track record. They will join an excellent a lively group of researchers. Mathematical acumen is essential; coding ability is a strong advantage. Study will begin with MRes level study for one year and move to doctoral level study the following three. The applicant will be expected in the highest quality forums, and to travel both in the UK and overseas to present their work.

This project is associated with the UKRI CDT in Accountable, Responsible and Transparent AI (ART-AI), which is looking for its first cohort of at least 10 students to start in September 2019. Students will be fully funded for 4 years (stipend, UK/EU tuition fees and research support budget). Further details can be found at: http://www.bath.ac.uk/research-centres/ukri-centre-for-doctoral-training-in-accountable-responsible-and-transparent-ai/.

Applicants should hold, or expect to receive, a First Class or good Upper Second Class Honours degree. A master’s level qualification would also be advantageous.

Informal enquiries about the project should be directed to Prof Peter Hall: .

Enquiries about the application process should be sent to .

Formal applications should be made via the University of Bath’s online application form for a PhD in Computer Science: https://samis.bath.ac.uk/urd/sits.urd/run/siw_ipp_lgn.login?process=siw_ipp_app&code1=RDUCM-FP01&code2=0013

Start date: 23 September 2019.

Funding Notes

ART-AI CDT studentships are available on a competition basis for UK and EU students for up to 4 years. Funding will cover UK/EU tuition fees as well as providing maintenance at the UKRI doctoral stipend rate (£15,009 per annum for 2019/20) and a training support fee of £1,000 per annum.

We also welcome all-year-round applications from self-funded candidates and candidates who can source their own funding.

References

1] Hall et al; Cross-depiction problem: Recognition and synthesis of photographs and artwork. CVM 2015.

[2] Wu, Cai, Hall; Learning graphs to model visual objects across different depictive styles, ECCV 2014.

How good is research at University of Bath in Computer Science and Informatics?

FTE Category A staff submitted: 24.00

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2019
All rights reserved.