PittsburghV1, Main, Exploration, bibRecord, 001228

Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity.

Identifieur interne : 001228 ( Main/Exploration ); précédent : 001227; suivant : 001229

Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity.

Auteurs : Lászl A. Jeni [États-Unis] ; András L Rincz [Hongrie] ; Zoltán Szab [Royaume-Uni] ; Jeffrey F. Cohn [États-Unis] ; Takeo Kanade [États-Unis]

Source :

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision ; 2014.

RBID : pubmed:27830214

Abstract

In many behavioral domains, such as facial expression and gesture, sparse structure is prevalent. This sparsity would be well suited for event detection but for one problem. Features typically are confounded by alignment error in space and time. As a consequence, high-dimensional representations such as SIFT and Gabor features have been favored despite their much greater computational cost and potential loss of information. We propose a Kernel Structured Sparsity (KSS) method that can handle both the temporal alignment problem and the structured sparse reconstruction within a common framework, and it can rely on simple features. We characterize spatio-temporal events as time-series of motion patterns and by utilizing time-series kernels we apply standard structured-sparse coding techniques to tackle this important problem. We evaluated the KSS method using both gesture and facial expression datasets that include spontaneous behavior and differ in degree of difficulty and type of ground truth coding. KSS outperformed both sparse and non-sparse methods that utilize complex image features and their temporal extensions. In the case of early facial event classification KSS had 10% higher accuracy as measured by F1 score over kernel SVM methods.

DOI: 10.1007/978-3-319-10593-2_10
PubMed: 27830214

Affiliations:

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity.</title>
<author><name sortKey="Jeni, Laszl A" sort="Jeni, Laszl A" uniqKey="Jeni L" first="Lászl A" last="Jeni">Lászl A. Jeni</name>
<affiliation wicri:level="4"><nlm:affiliation>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA.</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="L Rincz, Andras" sort="L Rincz, Andras" uniqKey="L Rincz A" first="András" last="L Rincz">András L Rincz</name>
<affiliation wicri:level="3"><nlm:affiliation>Faculty of Informatics, Eötvös Loránd University, Budapest, Hungary.</nlm:affiliation>
<country xml:lang="fr">Hongrie</country>
<wicri:regionArea>Faculty of Informatics, Eötvös Loránd University, Budapest</wicri:regionArea>
<placeName><settlement type="city">Budapest</settlement>
<region nuts="2">Hongrie centrale</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Szab, Zoltan" sort="Szab, Zoltan" uniqKey="Szab Z" first="Zoltán" last="Szab">Zoltán Szab</name>
<affiliation wicri:level="4"><nlm:affiliation>Gatsby Computational Neuroscience Unit, University College London, London, UK.</nlm:affiliation>
<country xml:lang="fr">Royaume-Uni</country>
<wicri:regionArea>Gatsby Computational Neuroscience Unit, University College London, London</wicri:regionArea>
<placeName><settlement type="city">Londres</settlement>
<region type="country">Angleterre</region>
<region type="région" nuts="1">Grand Londres</region>
<settlement type="city">Londres</settlement>
</placeName>
<orgName type="university">University College de Londres</orgName>
</affiliation>
</author>
<author><name sortKey="Cohn, Jeffrey F" sort="Cohn, Jeffrey F" uniqKey="Cohn J" first="Jeffrey F" last="Cohn">Jeffrey F. Cohn</name>
<affiliation wicri:level="4"><nlm:affiliation>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA; Department of Psychology, University of Pittsburgh, Pittsburgh, PA, USA.</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA; Department of Psychology, University of Pittsburgh, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="Kanade, Takeo" sort="Kanade, Takeo" uniqKey="Kanade T" first="Takeo" last="Kanade">Takeo Kanade</name>
<affiliation wicri:level="4"><nlm:affiliation>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA.</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2014">2014</date>
<idno type="RBID">pubmed:27830214</idno>
<idno type="pmid">27830214</idno>
<idno type="doi">10.1007/978-3-319-10593-2_10</idno>
<idno type="wicri:Area/PubMed/Corpus">004367</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">004367</idno>
<idno type="wicri:Area/PubMed/Curation">004327</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Curation">004327</idno>
<idno type="wicri:Area/PubMed/Checkpoint">004327</idno>
<idno type="wicri:explorRef" wicri:stream="Checkpoint" wicri:step="PubMed">004327</idno>
<idno type="wicri:Area/Ncbi/Merge">004A43</idno>
<idno type="wicri:Area/Ncbi/Curation">004A43</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">004A43</idno>
<idno type="wicri:Area/Main/Merge">001254</idno>
<idno type="wicri:Area/Main/Curation">001228</idno>
<idno type="wicri:Area/Main/Exploration">001228</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity.</title>
<author><name sortKey="Jeni, Laszl A" sort="Jeni, Laszl A" uniqKey="Jeni L" first="Lászl A" last="Jeni">Lászl A. Jeni</name>
<affiliation wicri:level="4"><nlm:affiliation>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA.</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="L Rincz, Andras" sort="L Rincz, Andras" uniqKey="L Rincz A" first="András" last="L Rincz">András L Rincz</name>
<affiliation wicri:level="3"><nlm:affiliation>Faculty of Informatics, Eötvös Loránd University, Budapest, Hungary.</nlm:affiliation>
<country xml:lang="fr">Hongrie</country>
<wicri:regionArea>Faculty of Informatics, Eötvös Loránd University, Budapest</wicri:regionArea>
<placeName><settlement type="city">Budapest</settlement>
<region nuts="2">Hongrie centrale</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Szab, Zoltan" sort="Szab, Zoltan" uniqKey="Szab Z" first="Zoltán" last="Szab">Zoltán Szab</name>
<affiliation wicri:level="4"><nlm:affiliation>Gatsby Computational Neuroscience Unit, University College London, London, UK.</nlm:affiliation>
<country xml:lang="fr">Royaume-Uni</country>
<wicri:regionArea>Gatsby Computational Neuroscience Unit, University College London, London</wicri:regionArea>
<placeName><settlement type="city">Londres</settlement>
<region type="country">Angleterre</region>
<region type="région" nuts="1">Grand Londres</region>
<settlement type="city">Londres</settlement>
</placeName>
<orgName type="university">University College de Londres</orgName>
</affiliation>
</author>
<author><name sortKey="Cohn, Jeffrey F" sort="Cohn, Jeffrey F" uniqKey="Cohn J" first="Jeffrey F" last="Cohn">Jeffrey F. Cohn</name>
<affiliation wicri:level="4"><nlm:affiliation>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA; Department of Psychology, University of Pittsburgh, Pittsburgh, PA, USA.</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA; Department of Psychology, University of Pittsburgh, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="Kanade, Takeo" sort="Kanade, Takeo" uniqKey="Kanade T" first="Takeo" last="Kanade">Takeo Kanade</name>
<affiliation wicri:level="4"><nlm:affiliation>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA.</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Robotics Institute, Carnegie Mellon University, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
</analytic>
<series><title level="j">Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision</title>
<imprint><date when="2014" type="published">2014</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">In many behavioral domains, such as facial expression and gesture, sparse structure is prevalent. This sparsity would be well suited for event detection but for one problem. Features typically are confounded by alignment error in space and time. As a consequence, high-dimensional representations such as SIFT and Gabor features have been favored despite their much greater computational cost and potential loss of information. We propose a Kernel Structured Sparsity (KSS) method that can handle both the temporal alignment problem and the structured sparse reconstruction within a common framework, and it can rely on simple features. We characterize spatio-temporal events as time-series of motion patterns and by utilizing time-series kernels we apply standard structured-sparse coding techniques to tackle this important problem. We evaluated the KSS method using both gesture and facial expression datasets that include spontaneous behavior and differ in degree of difficulty and type of ground truth coding. KSS outperformed both sparse and non-sparse methods that utilize complex image features and their temporal extensions. In the case of early facial event classification KSS had 10% higher accuracy as measured by F1 score over kernel SVM methods.</div>
</front>
</TEI>
<affiliations><list><country><li>Hongrie</li>
<li>Royaume-Uni</li>
<li>États-Unis</li>
</country>
<region><li>Angleterre</li>
<li>Grand Londres</li>
<li>Hongrie centrale</li>
<li>Pennsylvanie</li>
</region>
<settlement><li>Budapest</li>
<li>Londres</li>
<li>Pittsburgh</li>
</settlement>
<orgName><li>University College de Londres</li>
<li>Université Carnegie-Mellon</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Pennsylvanie"><name sortKey="Jeni, Laszl A" sort="Jeni, Laszl A" uniqKey="Jeni L" first="Lászl A" last="Jeni">Lászl A. Jeni</name>
</region>
<name sortKey="Cohn, Jeffrey F" sort="Cohn, Jeffrey F" uniqKey="Cohn J" first="Jeffrey F" last="Cohn">Jeffrey F. Cohn</name>
<name sortKey="Kanade, Takeo" sort="Kanade, Takeo" uniqKey="Kanade T" first="Takeo" last="Kanade">Takeo Kanade</name>
</country>
<country name="Hongrie"><region name="Hongrie centrale"><name sortKey="L Rincz, Andras" sort="L Rincz, Andras" uniqKey="L Rincz A" first="András" last="L Rincz">András L Rincz</name>
</region>
</country>
<country name="Royaume-Uni"><region name="Angleterre"><name sortKey="Szab, Zoltan" sort="Szab, Zoltan" uniqKey="Szab Z" first="Zoltán" last="Szab">Zoltán Szab</name>
</region>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Amérique/explor/PittsburghV1/Data/Main/Exploration

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001228 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001228 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Amérique
   |area=    PittsburghV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     pubmed:27830214
   |texte=   Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity.
}}

Pour générer des pages wiki

HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i   -Sk "pubmed:27830214" \
       | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd   \
       | NlmPubMed2Wicri -a PittsburghV1

This area was generated with Dilib version V0.6.38.
Data generation: Fri Jun 18 17:37:45 2021. Site generation: Fri Jun 18 18:15:47 2021

Serveur d'exploration sur Pittsburgh

Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity.

Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity.

Source :

Abstract

Links toward previous steps (curation, corpus...)

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri

Pour générer des pages wiki

	Serveur d'exploration sur Pittsburgh
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.