B. Krüger, J. Tautges, M. Müller, and A. Weber. Journal of Virtual Reality and Broadcasting, (July 2008)urn:nbn:de:0009-6-14197,, ISSN 1860-2037.
Abstract
In this paper, we investigate how a multilinear model can be used to represent human motion data. Based on technical modes (referring to degrees of freedom and number of frames) and natural modes that typically appear in the context of a motion capture session (referring to actor, style, and repetition), the motion data is encoded in form of a high-order tensor. This tensor is then reduced by using N-mode singular value decomposition. Our experiments show that the
reduced model approximates the original motion better then previously introduced PCA-based approaches. Furthermore, we discuss how the tensor representation may be used as a valuable tool for the synthesis of new motions.
%0 Journal Article
%1 KTMW08
%A Krüger, Björn
%A Tautges, Jochen
%A Müller, Meinard
%A Weber, Andreas
%D 2008
%E Herder, Jens
%J Journal of Virtual Reality and Broadcasting
%K 2008 5(2008)5 5.2008 DPPL DiPP Digital_Peer_Publishing_Initiative Digital_Peer_Publishing_License JVRB Journal_of_Virtual_Reality_and_Broadcasting MoCaDa Motion_Capture Motion_Data Open_Access Peer_Reviewed [KTMW08]
%N 5
%T Multi-Mode Tensor Representation of Motion Data
%V 5
%X In this paper, we investigate how a multilinear model can be used to represent human motion data. Based on technical modes (referring to degrees of freedom and number of frames) and natural modes that typically appear in the context of a motion capture session (referring to actor, style, and repetition), the motion data is encoded in form of a high-order tensor. This tensor is then reduced by using N-mode singular value decomposition. Our experiments show that the
reduced model approximates the original motion better then previously introduced PCA-based approaches. Furthermore, we discuss how the tensor representation may be used as a valuable tool for the synthesis of new motions.
@article{KTMW08,
abstract = {In this paper, we investigate how a multilinear model can be used to represent human motion data. Based on technical modes (referring to degrees of freedom and number of frames) and natural modes that typically appear in the context of a motion capture session (referring to actor, style, and repetition), the motion data is encoded in form of a high-order tensor. This tensor is then reduced by using N-mode singular value decomposition. Our experiments show that the
reduced model approximates the original motion better then previously introduced PCA-based approaches. Furthermore, we discuss how the tensor representation may be used as a valuable tool for the synthesis of new motions.},
added-at = {2008-08-12T16:46:48.000+0200},
author = {Kr{\"u}ger, Bj{\"o}rn and Tautges, Jochen and M{\"u}ller, Meinard and Weber, Andreas},
biburl = {https://www.bibsonomy.org/bibtex/24b909a06596b851d4daebf81b6a1819f/jvrb_regulski},
editor = {Herder, Jens},
interhash = {a7d6081ba56b6ca386111016072c461d},
intrahash = {4b909a06596b851d4daebf81b6a1819f},
journal = {Journal of Virtual Reality and Broadcasting},
keywords = {2008 5(2008)5 5.2008 DPPL DiPP Digital_Peer_Publishing_Initiative Digital_Peer_Publishing_License JVRB Journal_of_Virtual_Reality_and_Broadcasting MoCaDa Motion_Capture Motion_Data Open_Access Peer_Reviewed [KTMW08]},
month = {July},
note = {{\tt urn:nbn:de:0009-6-14197,}, ISSN 1860-2037},
number = 5,
timestamp = {2008-08-12T16:46:50.000+0200},
title = {Multi-Mode Tensor Representation of Motion Data},
volume = 5,
year = 2008
}