Output details
11 - Computer Science and Informatics
University of Aberdeen
Return to search
Output 0 of 0 in the submission
Article title
Incremental multi-linear discriminant analysis using canonical correlations for action recognition
Type
D - Journal article
Title of journal
Neurocomputing
Article number
-
Volume number
83
Issue number
-
First page of article
56
ISSN of journal
0925-2312
Year of publication
2012
URL
-
Number of additional authors
6
Additional information
<23>This paper shows how feature extraction is applied to real-world problems using tensor-based representations. The techniques presented in this paper obtained world-leading performances on standard action recognition benchmarks (the Weizmann Database). The method proposed in this paper could provide a significantly faster and more robust approach to action recognition problems. This is joint work with researchers from leading Chinese universities and a major American industrial cooperation (Raytheon), which highlights strong international collaboration links.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
2
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-