Position:
PhD (CASE) Studentship in multimedia signal processing (3
years)
Location:
London, UK
Title: Audiovisual semantic discovery
Applications are invited for a
CASE PhD studentship with the Digital Signal Processing and
Multimedia Research Group of the Electronic Engineering
Department, Queen Mary, University of
London in collaboration with BT
Group CTO Research and Venturing.
Project description:
One of the goals of
dynamic scene analysis and understanding is to find unusual
patterns (events, interactions) in large collections of
audiovisual material. Unusual patterns may be rare events or
specific interactions. Rare events and interactions are not
necessarily easy to model or to predict. The aim of this PhD
research project is to address the scene understanding problem
by exploring the use of unsupervised dimensionality reduction
by isometric mapping and machine learning. Isometric mapping
aims at finding meaningful low-dimensional structures,
representing patterns, events and interactions, hidden in
their high-dimensional observations. The features to be used
will be based on both visual and acoustic information.
Acoustic information allows one to disambiguate between events
that would appear similar based on visual information only.
Furthermore, additional information will be provided by the
use of data captured by multiple sensors in order to discover
events on a larger scale than that enabled by the use of one
sensor only. The isometric mapping will generate the embedding
of the data under analysis that in turn will enable the
discovering of spatio-temporal structures corresponding to
meaningful events. Data clustering will be used to separate
different events and to detect abnormal events. In addition to
the above, given the nature of the application, privacy issues
will be considered for data collection and visualisation. The
objective is to ensure that the proposed system is accepted by
the end users and the general public.
Workplace:
The normal place of
work will be Queen Mary, University of London, but the
candidate will have the opportunity to spend some periods,
distributed over the project life and totalling a minimum of 3
months, within BT. The successful candidate will join an
expanding research group engaged in a variety of national and
international projects on digital media and content
technologies.
Queen Mary, University of London is situated in Mile End,
bordering Regents Canal, close to Canary Wharf (the new,
modern and commercial part of London) and to the City of
London (
http://www.qmul.ac.uk
).
Eligibility:
The studentship is
open to UK and EU students only.
For UK residents it covers the cost of home student tuition
fees as well as a tax-free EPSRC maintenance stipend (
http://www.epsrc.ac.uk ).
For EU students it only covers the cost of tuition fees and
does not include a maintenance stipend. In addition, for both
UK and EU students, a stipend contribution of GBP 3,000 per annum
will be made by the CASE sponsor.
Applicants must have a first degree in mathematical science,
physics, statistics, computer science, electronic engineering
or allied disciplines (minimum 2:1 or equivalent), and excellent mathematical and programming skills. Previous
experience of digital signal processing or computer vision is
desirable, although not mandatory.
Application:
Applicants should follow the
guidelines that can be found at
http://www.elec.qmul.ac.uk/study/phd/res-stud.htm
Fon informal
enquiries
and deadline:
contact Dr Andrea Cavallaro (
andrea.cavallaro@elec.qmul.ac.uk )
Links:
DSP and Multimedia Group:
http://www.elec.qmul.ac.uk/research/dsp/index.html
BT Group CTO Research and Venturing:
http://www.bt.com
|