BMVA
British Machine Vision Association and Society for Pattern Recognition
http://www.bmva.org/meetings
Call for Participation
Temporal Pattern Learning and Recognition
One Day BMVA technical meeting in London, UK, on 22nd September 2010
Chair: Andrew Gilbert and Eng Jon Ong (University of Surrey)
The learning of temporal based patterns has seen a large increase in
interest within the last few years. Significant interest has been driven
through the potential in applications where major events can be detected
by recognising specific actions or patterns, for example, the scoring of
a goal, people hugging, or some furtive behaviour in a surveillance
image. Additionally, there is increasing interest in expression and
gesture recognition for use in affective computing systems. All these
bring about the need for automatic video analysis and the recognition of
events that are inherently temporal in nature.
Much of the progress has been made through incorporating ideas from
single frame object recognition and adapting them for temporal based
action recognition. However this might not provide the optimal approach
in terms of speed or accuracy. One exciting and relatively untapped area
of research that may offer potential solutions to the above issues is
that of data mining. Particularly useful to the task of learning and
recognising temporal patterns is research in sequential pattern mining.
This meeting aims to highlight and thus seek papers on recent
state-of-the-art learning and recognition methods of various types of
temporal visual patterns (e.g. gesture, action recognition, etc...). In
addition to this, we also seek work in the field of data mining, in
particular that of sequential pattern mining for recognition of temporal
patterns. Areas of interest include the following:
- Sequential Pattern Mining
- Feature Extraction for Recognition
- Gesture Recognition
- Automated Visual Lip-reading
- Activity and Action Recognition
- Gait Analysis and Classification
- Fusion methods for Recognition
- Facial Expression Analysis and Recognition
- Non-verbal Cue Analysis
- Sign-language Recognition
- Behaviour and Scene Analysis
Other topics within the broad domain of temporal pattern learning will
also be considered for inclusion.
Please submit an extended summary of about one A4-sized page length (no
longer than 2 pages) in length (PDF preferred). Send Abstracts by email
attachment (5Mb max please) to Andrew Gilbert ([log in to unmask])
by 14th July 2010.
--
Dr Dimitrios Makris
Senior Lecturer
Faculty of Computing, Information Systems and Mathematics
Kingston University, London
Tel: +44 20 8417 7082
Email: [log in to unmask] <mailto:[log in to unmask]>
Web: staffnet.kingston.ac.uk/~ku32195/
<http://staffnet.kingston.ac.uk/%7Eku32195/>
This email has been scanned for all viruses by the MessageLabs Email
Security System.
|