People Watching: Human Actions as a Cue for Single View Geometry
Identifieur interne : 000317 ( France/Analysis ); précédent : 000316; suivant : 000318People Watching: Human Actions as a Cue for Single View Geometry
Auteurs : David F. Fouhey [États-Unis] ; Vincent Delaitre [France] ; Abhinav Gupta [États-Unis] ; Alexei A. Efros [États-Unis] ; Ivan Laptev [France] ; Josef Sivic [France]Source :
- International journal of computer vision [ 0920-5691 ] ; 2014.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Multimédia.
English descriptors
- KwdEn :
Abstract
We present an approach which exploits the coupling between human actions and scene geometry to use human pose as a cue for single-view 3D scene understanding. Our method builds upon recent advances in still-image pose estimation to extract functional and geometric constraints on the scene. These constraints are then used to improve single-view 3D scene understanding approaches. The proposed method is validated on monocular time-lapse sequences from YouTube and still images of indoor scenes gathered from the Internet. We demonstrate that observing people performing different actions can significantly improve estimates of 3D scene geometry.
Url:
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000278
- to stream PascalFrancis, to step Curation: 004311
- to stream PascalFrancis, to step Checkpoint: 000473
- to stream Main, to step Merge: 005396
- to stream Hal, to step Corpus: 000457
- to stream Hal, to step Curation: 000457
- to stream Hal, to step Checkpoint: 000227
- to stream Main, to step Merge: 000715
- to stream Main, to step Curation: 005124
- to stream Main, to step Exploration: 005124
- to stream France, to step Extraction: 000317
Links to Exploration step
Pascal:15-0003765Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">People Watching: Human Actions as a Cue for Single View Geometry</title>
<author><name sortKey="Fouhey, David F" sort="Fouhey, David F" uniqKey="Fouhey D" first="David F." last="Fouhey">David F. Fouhey</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue</s1>
<s2>Pittsburgh, PA 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Pittsburgh, PA 15213</wicri:noRegion>
<orgName type="university">Université Carnegie-Mellon</orgName>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Delaitre, Vincent" sort="Delaitre, Vincent" uniqKey="Delaitre V" first="Vincent" last="Delaitre">Vincent Delaitre</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>WILLOW Project, Departement d'Informatique de l'École Normale Supérieure, ENS/INRIA/CNRS UMR 8548, 23, Avenue d'Italie</s1>
<s2>75013 Paris</s2>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>75013 Paris</wicri:noRegion>
<placeName><settlement type="city">Paris</settlement>
<region type="région" nuts="2">Île-de-France</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Gupta, Abhinav" sort="Gupta, Abhinav" uniqKey="Gupta A" first="Abhinav" last="Gupta">Abhinav Gupta</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue</s1>
<s2>Pittsburgh, PA 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Pittsburgh, PA 15213</wicri:noRegion>
<orgName type="university">Université Carnegie-Mellon</orgName>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Efros, Alexei A" sort="Efros, Alexei A" uniqKey="Efros A" first="Alexei A." last="Efros">Alexei A. Efros</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue</s1>
<s2>Pittsburgh, PA 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Pittsburgh, PA 15213</wicri:noRegion>
<orgName type="university">Université Carnegie-Mellon</orgName>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Laptev, Ivan" sort="Laptev, Ivan" uniqKey="Laptev I" first="Ivan" last="Laptev">Ivan Laptev</name>
<affiliation wicri:level="3"><inist:fA14 i1="02"><s1>WILLOW Project, Departement d'Informatique de l'École Normale Supérieure, ENS/INRIA/CNRS UMR 8548, 23, Avenue d'Italie</s1>
<s2>75013 Paris</s2>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Île-de-France</region>
<settlement type="city">Paris</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Sivic, Josef" sort="Sivic, Josef" uniqKey="Sivic J" first="Josef" last="Sivic">Josef Sivic</name>
<affiliation wicri:level="3"><inist:fA14 i1="02"><s1>WILLOW Project, Departement d'Informatique de l'École Normale Supérieure, ENS/INRIA/CNRS UMR 8548, 23, Avenue d'Italie</s1>
<s2>75013 Paris</s2>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Île-de-France</region>
<settlement type="city">Paris</settlement>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">15-0003765</idno>
<date when="2014">2014</date>
<idno type="stanalyst">PASCAL 15-0003765 INIST</idno>
<idno type="RBID">Pascal:15-0003765</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000278</idno>
<idno type="wicri:Area/PascalFrancis/Curation">004311</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000473</idno>
<idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000473</idno>
<idno type="wicri:doubleKey">0920-5691:2014:Fouhey D:people:watching:human</idno>
<idno type="wicri:Area/Main/Merge">005396</idno>
<idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:hal-01066257</idno>
<idno type="url">https://hal.inria.fr/hal-01066257</idno>
<idno type="wicri:Area/Hal/Corpus">000457</idno>
<idno type="wicri:Area/Hal/Curation">000457</idno>
<idno type="wicri:Area/Hal/Checkpoint">000227</idno>
<idno type="wicri:explorRef" wicri:stream="Hal" wicri:step="Checkpoint">000227</idno>
<idno type="wicri:doubleKey">0920-5691:2014:Fouhey D:people:watching:human</idno>
<idno type="wicri:Area/Main/Merge">000715</idno>
<idno type="wicri:Area/Main/Curation">005124</idno>
<idno type="wicri:Area/Main/Exploration">005124</idno>
<idno type="wicri:Area/France/Extraction">000317</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">People Watching: Human Actions as a Cue for Single View Geometry</title>
<author><name sortKey="Fouhey, David F" sort="Fouhey, David F" uniqKey="Fouhey D" first="David F." last="Fouhey">David F. Fouhey</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue</s1>
<s2>Pittsburgh, PA 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Pittsburgh, PA 15213</wicri:noRegion>
<orgName type="university">Université Carnegie-Mellon</orgName>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Delaitre, Vincent" sort="Delaitre, Vincent" uniqKey="Delaitre V" first="Vincent" last="Delaitre">Vincent Delaitre</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>WILLOW Project, Departement d'Informatique de l'École Normale Supérieure, ENS/INRIA/CNRS UMR 8548, 23, Avenue d'Italie</s1>
<s2>75013 Paris</s2>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>75013 Paris</wicri:noRegion>
<placeName><settlement type="city">Paris</settlement>
<region type="région" nuts="2">Île-de-France</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Gupta, Abhinav" sort="Gupta, Abhinav" uniqKey="Gupta A" first="Abhinav" last="Gupta">Abhinav Gupta</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue</s1>
<s2>Pittsburgh, PA 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Pittsburgh, PA 15213</wicri:noRegion>
<orgName type="university">Université Carnegie-Mellon</orgName>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Efros, Alexei A" sort="Efros, Alexei A" uniqKey="Efros A" first="Alexei A." last="Efros">Alexei A. Efros</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue</s1>
<s2>Pittsburgh, PA 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Pittsburgh, PA 15213</wicri:noRegion>
<orgName type="university">Université Carnegie-Mellon</orgName>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Laptev, Ivan" sort="Laptev, Ivan" uniqKey="Laptev I" first="Ivan" last="Laptev">Ivan Laptev</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>WILLOW Project, Departement d'Informatique de l'École Normale Supérieure, ENS/INRIA/CNRS UMR 8548, 23, Avenue d'Italie</s1>
<s2>75013 Paris</s2>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>75013 Paris</wicri:noRegion>
<placeName><settlement type="city">Paris</settlement>
<region type="région" nuts="2">Île-de-France</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Sivic, Josef" sort="Sivic, Josef" uniqKey="Sivic J" first="Josef" last="Sivic">Josef Sivic</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>WILLOW Project, Departement d'Informatique de l'École Normale Supérieure, ENS/INRIA/CNRS UMR 8548, 23, Avenue d'Italie</s1>
<s2>75013 Paris</s2>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>75013 Paris</wicri:noRegion>
<placeName><settlement type="city">Paris</settlement>
<region type="région" nuts="2">Île-de-France</region>
</placeName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">International journal of computer vision</title>
<title level="j" type="abbreviated">Int. j. comput. vis.</title>
<idno type="ISSN">0920-5691</idno>
<imprint><date when="2014">2014</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">International journal of computer vision</title>
<title level="j" type="abbreviated">Int. j. comput. vis.</title>
<idno type="ISSN">0920-5691</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Action</term>
<term>Behavioral analysis</term>
<term>Computer vision</term>
<term>Fixed image</term>
<term>Image processing</term>
<term>Image reconstruction</term>
<term>Indoor installation</term>
<term>Internet</term>
<term>Monocular vision</term>
<term>Motion estimation</term>
<term>Multimedia</term>
<term>Posture</term>
<term>Scene analysis</term>
<term>Tridimensional image</term>
<term>Video signal</term>
<term>Web site</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Analyse scène</term>
<term>Image fixe</term>
<term>Vision ordinateur</term>
<term>Multimédia</term>
<term>Signal vidéo</term>
<term>Internet</term>
<term>Image tridimensionnelle</term>
<term>Analyse comportementale</term>
<term>Action</term>
<term>Estimation mouvement</term>
<term>Reconstruction image</term>
<term>Traitement image</term>
<term>Posture</term>
<term>Vision monoculaire</term>
<term>Site Web</term>
<term>Installation intérieure</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Multimédia</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">We present an approach which exploits the coupling between human actions and scene geometry to use human pose as a cue for single-view 3D scene understanding. Our method builds upon recent advances in still-image pose estimation to extract functional and geometric constraints on the scene. These constraints are then used to improve single-view 3D scene understanding approaches. The proposed method is validated on monocular time-lapse sequences from YouTube and still images of indoor scenes gathered from the Internet. We demonstrate that observing people performing different actions can significantly improve estimates of 3D scene geometry.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
<li>États-Unis</li>
</country>
<region><li>Pennsylvanie</li>
<li>Île-de-France</li>
</region>
<settlement><li>Paris</li>
<li>Pittsburgh</li>
</settlement>
<orgName><li>Université Carnegie-Mellon</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Pennsylvanie"><name sortKey="Fouhey, David F" sort="Fouhey, David F" uniqKey="Fouhey D" first="David F." last="Fouhey">David F. Fouhey</name>
</region>
<name sortKey="Efros, Alexei A" sort="Efros, Alexei A" uniqKey="Efros A" first="Alexei A." last="Efros">Alexei A. Efros</name>
<name sortKey="Gupta, Abhinav" sort="Gupta, Abhinav" uniqKey="Gupta A" first="Abhinav" last="Gupta">Abhinav Gupta</name>
</country>
<country name="France"><region name="Île-de-France"><name sortKey="Delaitre, Vincent" sort="Delaitre, Vincent" uniqKey="Delaitre V" first="Vincent" last="Delaitre">Vincent Delaitre</name>
</region>
<name sortKey="Laptev, Ivan" sort="Laptev, Ivan" uniqKey="Laptev I" first="Ivan" last="Laptev">Ivan Laptev</name>
<name sortKey="Sivic, Josef" sort="Sivic, Josef" uniqKey="Sivic J" first="Josef" last="Sivic">Josef Sivic</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Amérique/explor/PittsburghV1/Data/France/Analysis
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000317 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/France/Analysis/biblio.hfd -nk 000317 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Amérique |area= PittsburghV1 |flux= France |étape= Analysis |type= RBID |clé= Pascal:15-0003765 |texte= People Watching: Human Actions as a Cue for Single View Geometry }}
This area was generated with Dilib version V0.6.38. |