Home / Issues / 5.2008 / Multi-Mode Tensor Representation of Motion Data
Document Actions

Citation and metadata

Recommended citation

Björn Krüger, Jochen Tautges, Meinard Müller, and Andreas Weber, Multi-Mode Tensor Representation of Motion Data. JVRB - Journal of Virtual Reality and Broadcasting, 5(2008), no. 5. (urn:nbn:de:0009-6-14197)

Download Citation

Endnote

%0 Journal Article
%T Multi-Mode Tensor Representation of Motion Data
%A Krüger, Björn
%A Tautges, Jochen
%A Müller, Meinard
%A Weber, Andreas
%J JVRB - Journal of Virtual Reality and Broadcasting
%D 2008
%V 5(2008)
%N 5
%@ 1860-2037
%F krüger2008
%X In this paper, we investigate how a multilinear modelcan be used to represent human motion data. Basedon technical modes (referring to degrees of freedomand number of frames) and natural modes that typicallyappear in the context of a motion capture session(referring to actor, style, and repetition), the motiondata is encoded in form of a high-order tensor.This tensor is then reduced by using N-mode singularvalue decomposition. Our experiments show that thereduced model approximates the original motion betterthen previously introduced PCA-based approaches.Furthermore, we discuss how the tensor representationmay be used as a valuable tool for the synthesis of newmotions.
%L 004
%K Motion Capture
%K Motion Synthesis
%K N-Mode SVD
%K Tensor Representation
%R 10.20385/1860-2037/5.2008.5
%U http://nbn-resolving.de/urn:nbn:de:0009-6-14197
%U http://dx.doi.org/10.20385/1860-2037/5.2008.5

Download

Bibtex

@Article{krüger2008,
  author = 	"Kr{\"u}ger, Bj{\"o}rn
		and Tautges, Jochen
		and M{\"u}ller, Meinard
		and Weber, Andreas",
  title = 	"Multi-Mode Tensor Representation of Motion Data",
  journal = 	"JVRB - Journal of Virtual Reality and Broadcasting",
  year = 	"2008",
  volume = 	"5(2008)",
  number = 	"5",
  keywords = 	"Motion Capture; Motion Synthesis; N-Mode SVD; Tensor Representation",
  abstract = 	"In this paper, we investigate how a multilinear modelcan be used to represent human motion data. Basedon technical modes (referring to degrees of freedomand number of frames) and natural modes that typicallyappear in the context of a motion capture session(referring to actor, style, and repetition), the motiondata is encoded in form of a high-order tensor.This tensor is then reduced by using N-mode singularvalue decomposition. Our experiments show that thereduced model approximates the original motion betterthen previously introduced PCA-based approaches.Furthermore, we discuss how the tensor representationmay be used as a valuable tool for the synthesis of newmotions.",
  issn = 	"1860-2037",
  doi = 	"10.20385/1860-2037/5.2008.5",
  url = 	"http://nbn-resolving.de/urn:nbn:de:0009-6-14197"
}

Download

RIS

TY  - JOUR
AU  - Krüger, Björn
AU  - Tautges, Jochen
AU  - Müller, Meinard
AU  - Weber, Andreas
PY  - 2008
DA  - 2008//
TI  - Multi-Mode Tensor Representation of Motion Data
JO  - JVRB - Journal of Virtual Reality and Broadcasting
VL  - 5(2008)
IS  - 5
KW  - Motion Capture
KW  - Motion Synthesis
KW  - N-Mode SVD
KW  - Tensor Representation
AB  - In this paper, we investigate how a multilinear modelcan be used to represent human motion data. Basedon technical modes (referring to degrees of freedomand number of frames) and natural modes that typicallyappear in the context of a motion capture session(referring to actor, style, and repetition), the motiondata is encoded in form of a high-order tensor.This tensor is then reduced by using N-mode singularvalue decomposition. Our experiments show that thereduced model approximates the original motion betterthen previously introduced PCA-based approaches.Furthermore, we discuss how the tensor representationmay be used as a valuable tool for the synthesis of newmotions.
SN  - 1860-2037
UR  - http://nbn-resolving.de/urn:nbn:de:0009-6-14197
DO  - 10.20385/1860-2037/5.2008.5
ID  - krüger2008
ER  - 
Download

Wordbib

<?xml version="1.0" encoding="UTF-8"?>
<b:Sources SelectedStyle="" xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography"  xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" >
<b:Source>
<b:Tag>krüger2008</b:Tag>
<b:SourceType>ArticleInAPeriodical</b:SourceType>
<b:Year>2008</b:Year>
<b:PeriodicalTitle>JVRB - Journal of Virtual Reality and Broadcasting</b:PeriodicalTitle>
<b:Volume>5(2008)</b:Volume>
<b:Issue>5</b:Issue>
<b:Url>http://nbn-resolving.de/urn:nbn:de:0009-6-14197</b:Url>
<b:Url>http://dx.doi.org/10.20385/1860-2037/5.2008.5</b:Url>
<b:Author>
<b:Author><b:NameList>
<b:Person><b:Last>Krüger</b:Last><b:First>Björn</b:First></b:Person>
<b:Person><b:Last>Tautges</b:Last><b:First>Jochen</b:First></b:Person>
<b:Person><b:Last>Müller</b:Last><b:First>Meinard</b:First></b:Person>
<b:Person><b:Last>Weber</b:Last><b:First>Andreas</b:First></b:Person>
</b:NameList></b:Author>
</b:Author>
<b:Title>Multi-Mode Tensor Representation of Motion Data</b:Title>
<b:Comments>In this paper, we investigate how a multilinear modelcan be used to represent human motion data. Basedon technical modes (referring to degrees of freedomand number of frames) and natural modes that typicallyappear in the context of a motion capture session(referring to actor, style, and repetition), the motiondata is encoded in form of a high-order tensor.This tensor is then reduced by using N-mode singularvalue decomposition. Our experiments show that thereduced model approximates the original motion betterthen previously introduced PCA-based approaches.Furthermore, we discuss how the tensor representationmay be used as a valuable tool for the synthesis of newmotions.</b:Comments>
</b:Source>
</b:Sources>
Download

ISI

PT Journal
AU Krüger, B
   Tautges, J
   Müller, M
   Weber, A
TI Multi-Mode Tensor Representation of Motion Data
SO JVRB - Journal of Virtual Reality and Broadcasting
PY 2008
VL 5(2008)
IS 5
DI 10.20385/1860-2037/5.2008.5
DE Motion Capture; Motion Synthesis; N-Mode SVD; Tensor Representation
AB In this paper, we investigate how a multilinear modelcan be used to represent human motion data. Basedon technical modes (referring to degrees of freedomand number of frames) and natural modes that typicallyappear in the context of a motion capture session(referring to actor, style, and repetition), the motiondata is encoded in form of a high-order tensor.This tensor is then reduced by using N-mode singularvalue decomposition. Our experiments show that thereduced model approximates the original motion betterthen previously introduced PCA-based approaches.Furthermore, we discuss how the tensor representationmay be used as a valuable tool for the synthesis of newmotions.
ER

Download

Mods

<mods>
  <titleInfo>
    <title>Multi-Mode Tensor Representation of Motion Data</title>
  </titleInfo>
  <name type="personal">
    <namePart type="family">Krüger</namePart>
    <namePart type="given">Björn</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Tautges</namePart>
    <namePart type="given">Jochen</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Müller</namePart>
    <namePart type="given">Meinard</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Weber</namePart>
    <namePart type="given">Andreas</namePart>
  </name>
  <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.</abstract>
  <subject>
    <topic>Motion Capture</topic>
    <topic>Motion Synthesis</topic>
    <topic>N-Mode SVD</topic>
    <topic>Tensor Representation</topic>
  </subject>
  <classification authority="ddc">004</classification>
  <relatedItem type="host">
    <genre authority="marcgt">periodical</genre>
    <genre>academic journal</genre>
    <titleInfo>
      <title>JVRB - Journal of Virtual Reality and Broadcasting</title>
    </titleInfo>
    <part>
      <detail type="volume">
        <number>5(2008)</number>
      </detail>
      <detail type="issue">
        <number>5</number>
      </detail>
      <date>2008</date>
    </part>
  </relatedItem>
  <identifier type="issn">1860-2037</identifier>
  <identifier type="urn">urn:nbn:de:0009-6-14197</identifier>
  <identifier type="doi">10.20385/1860-2037/5.2008.5</identifier>
  <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-6-14197</identifier>
  <identifier type="citekey">krüger2008</identifier>
</mods>
Download

Full Metadata