For the current REF see the REF 2021 website REF 2021 logo

Output details

11 - Computer Science and Informatics

Imperial College London

Return to search Previous output Next output
Output 8 of 201 in the submission
Article title

A Dynamic Texture-Based Approach to Recognition of Facial Actions and Their Temporal Models

Type
D - Journal article
Title of journal
IEEE Transactions on Pattern Analysis and Machine Intelligence
Article number
-
Volume number
32
Issue number
11
First page of article
1940
ISSN of journal
0162-8828
Year of publication
2010
URL
-
Number of additional authors
2
Additional information

<23>The paper describes a very novel dynamic-texture-based approach to recognition of facial expressions and their dynamics. The proposed approach has improved several aspects of facial muscle action (AU) detection in face video including the number of AUs handled, the overall accuracy of the recognition, and the accuracy of AUs’ temporal segments (onset, apex, offset) recognition. It is an extension of the IEEE Automatic Face and Gesture Recognition 2008 conference paper - Best Student Paper Award (to Sander Koelstra). IEEE TPAMI is the top journal in this area.

Interdisciplinary
-
Cross-referral requested
-
Research group
C - Visual Information Processing
Citation count
44
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-