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

Output details

11 - Computer Science and Informatics

Liverpool John Moores University

Return to search Previous output Next output
Output 0 of 0 in the submission
Article title

Human motion generation with multifactor models

Type
D - Journal article
Title of journal
COMPUTER ANIMATION AND VIRTUAL WORLDS
Article number
-
Volume number
22
Issue number
4
First page of article
351
ISSN of journal
1546-4261
Year of publication
2011
URL
-
Number of additional authors
3
Additional information

<26> The paper proposes a novel model for generating motions with multiple factors. It pioneered innovative use of motion databases and MICA (multilinear independent component analysis) for motion generation, combining ICA with invariant feature subspaces, to perform style transfer more precisely in an automated way. New motions are synthesised by interpolation and solving optimization problems for specific factors. The experiments prove it efficient for interactive motion synthesis. The paper was selected one of the best papers of CASA-2011 for special issue of the journal. The work is the outcome of collaboration between El Rhalibi and the other authors in China.

Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
0
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-