Output details
11 - Computer Science and Informatics
Queen Mary University of London
Article title
Learning Behavioural Context
Type
D - Journal article
Title of journal
International Journal of Computer Vision
Article number
-
Volume number
97
Issue number
3
First page of article
276
ISSN of journal
0920-5691
Year of publication
2012
URL
-
Number of additional authors
2
Additional information
<23>This paper defines the concept of behavioural context and demonstrates its great usefulness for video based complex behaviour recognition and anomaly detection. Extension of widely cited early work in ECCV'08 (10.1007/978-3-540-88693-8_28). The concept has inspired the work on crowd context at Univ. of Michigan (Choi et al, CVPR'11, 10.1109/CVPR.2011.5995707). The proposed algorithm has been integrated into the vsMatrix engine developed by VisionSemantics Ltd (contact person B. Koger, rpkoger@visionsemantics.com) and licensed to Keda Julong Group, China for banking environment intelligent surveillance applications (contact person C. Ma, msc@julong.cc).
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
4
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
