Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters
Identifieur interne : 000399 ( Istex/Corpus ); précédent : 000398; suivant : 000400Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters
Auteurs : Stephan Gammeter ; Till Quack ; David Tingdahl ; Luc Van GoolSource :
- Lecture Notes in Computer Science [ 0302-9743 ]
Abstract
Abstract: Most of the recent work on image-based object recognition and 3D reconstruction has focused on improving the underlying algorithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also affects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clusters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make object recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Furthermore, the methods are completely data-driven and fully automatic.
Url:
DOI: 10.1007/978-3-642-15549-9_53
Links to Exploration step
ISTEX:F010BB5C335677A88726C68AF0EC082316831FF3Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title><author><name sortKey="Gammeter, Stephan" sort="Gammeter, Stephan" uniqKey="Gammeter S" first="Stephan" last="Gammeter">Stephan Gammeter</name><affiliation><mods:affiliation>BIWI, ETH Zürich, </mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: gammeter@vision.ee.ethz.ch</mods:affiliation></affiliation></author><author><name sortKey="Quack, Till" sort="Quack, Till" uniqKey="Quack T" first="Till" last="Quack">Till Quack</name><affiliation><mods:affiliation>BIWI, ETH Zürich, </mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: tquack@vision.ee.ethz.ch</mods:affiliation></affiliation></author><author><name sortKey="Tingdahl, David" sort="Tingdahl, David" uniqKey="Tingdahl D" first="David" last="Tingdahl">David Tingdahl</name><affiliation><mods:affiliation>VISICS, K.U. Leuven, </mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: david.tingdahl@esat.kuleuven.be</mods:affiliation></affiliation></author><author><name sortKey="Van Gool, Luc" sort="Van Gool, Luc" uniqKey="Van Gool L" first="Luc" last="Van Gool">Luc Van Gool</name><affiliation><mods:affiliation>BIWI, ETH Zürich, </mods:affiliation></affiliation><affiliation><mods:affiliation>VISICS, K.U. Leuven, </mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: vangool@vision.ee.ethz.ch</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:F010BB5C335677A88726C68AF0EC082316831FF3</idno><date when="2010" year="2010">2010</date><idno type="doi">10.1007/978-3-642-15549-9_53</idno><idno type="url">https://api.istex.fr/ark:/67375/HCB-BC0JQ01W-G/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">000399</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000399</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title><author><name sortKey="Gammeter, Stephan" sort="Gammeter, Stephan" uniqKey="Gammeter S" first="Stephan" last="Gammeter">Stephan Gammeter</name><affiliation><mods:affiliation>BIWI, ETH Zürich, </mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: gammeter@vision.ee.ethz.ch</mods:affiliation></affiliation></author><author><name sortKey="Quack, Till" sort="Quack, Till" uniqKey="Quack T" first="Till" last="Quack">Till Quack</name><affiliation><mods:affiliation>BIWI, ETH Zürich, </mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: tquack@vision.ee.ethz.ch</mods:affiliation></affiliation></author><author><name sortKey="Tingdahl, David" sort="Tingdahl, David" uniqKey="Tingdahl D" first="David" last="Tingdahl">David Tingdahl</name><affiliation><mods:affiliation>VISICS, K.U. Leuven, </mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: david.tingdahl@esat.kuleuven.be</mods:affiliation></affiliation></author><author><name sortKey="Van Gool, Luc" sort="Van Gool, Luc" uniqKey="Van Gool L" first="Luc" last="Van Gool">Luc Van Gool</name><affiliation><mods:affiliation>BIWI, ETH Zürich, </mods:affiliation></affiliation><affiliation><mods:affiliation>VISICS, K.U. Leuven, </mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: vangool@vision.ee.ethz.ch</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="s" type="main" xml:lang="en">Lecture Notes in Computer Science</title><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Most of the recent work on image-based object recognition and 3D reconstruction has focused on improving the underlying algorithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also affects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clusters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make object recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Furthermore, the methods are completely data-driven and fully automatic.</div></front></TEI><istex><corpusName>springer-ebooks</corpusName><author><json:item><name>Stephan Gammeter</name><affiliations><json:string>BIWI, ETH Zürich,</json:string><json:string>E-mail: gammeter@vision.ee.ethz.ch</json:string></affiliations></json:item><json:item><name>Till Quack</name><affiliations><json:string>BIWI, ETH Zürich,</json:string><json:string>E-mail: tquack@vision.ee.ethz.ch</json:string></affiliations></json:item><json:item><name>David Tingdahl</name><affiliations><json:string>VISICS, K.U. Leuven,</json:string><json:string>E-mail: david.tingdahl@esat.kuleuven.be</json:string></affiliations></json:item><json:item><name>Luc van Gool</name><affiliations><json:string>BIWI, ETH Zürich,</json:string><json:string>VISICS, K.U. Leuven,</json:string><json:string>E-mail: vangool@vision.ee.ethz.ch</json:string></affiliations></json:item></author><arkIstex>ark:/67375/HCB-BC0JQ01W-G</arkIstex><language><json:string>eng</json:string></language><originalGenre><json:string>OriginalPaper</json:string></originalGenre><abstract>Abstract: Most of the recent work on image-based object recognition and 3D reconstruction has focused on improving the underlying algorithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also affects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clusters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make object recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Furthermore, the methods are completely data-driven and fully automatic.</abstract><qualityIndicators><score>8.464</score><pdfWordCount>5410</pdfWordCount><pdfCharCount>31460</pdfCharCount><pdfVersion>1.3</pdfVersion><pdfPageCount>14</pdfPageCount><pdfPageSize>430 x 660 pts</pdfPageSize><refBibsNative>false</refBibsNative><abstractWordCount>122</abstractWordCount><abstractCharCount>840</abstractCharCount><keywordCount>0</keywordCount></qualityIndicators><title>Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title><chapterId><json:string>53</json:string><json:string>Chap53</json:string></chapterId><genre><json:string>conference</json:string></genre><serie><title>Lecture Notes in Computer Science</title><language><json:string>unknown</json:string></language><copyrightDate>2010</copyrightDate><issn><json:string>0302-9743</json:string></issn><eissn><json:string>1611-3349</json:string></eissn><author><json:item><name>David Hutchison</name><affiliations><json:string>Lancaster University, Lancaster, UK</json:string></affiliations></json:item><json:item><name>Takeo Kanade</name><affiliations><json:string>Carnegie Mellon University, Pittsburgh, PA, USA</json:string></affiliations></json:item><json:item><name>Josef Kittler</name><affiliations><json:string>University of Surrey, Guildford, UK</json:string></affiliations></json:item><json:item><name>Jon M. Kleinberg</name><affiliations><json:string>Cornell University, Ithaca, NY, USA</json:string></affiliations></json:item><json:item><name>Friedemann Mattern</name><affiliations><json:string>ETH Zurich, Zurich, Switzerland</json:string></affiliations></json:item><json:item><name>John C. Mitchell</name><affiliations><json:string>Stanford University, Stanford, CA, USA</json:string></affiliations></json:item><json:item><name>Moni Naor</name><affiliations><json:string>Weizmann Institute of Science, Rehovot, Israel</json:string></affiliations></json:item><json:item><name>Oscar Nierstrasz</name><affiliations><json:string>University of Bern, Bern, Switzerland</json:string></affiliations></json:item><json:item><name>C. Pandu Rangan</name><affiliations><json:string>Indian Institute of Technology, Madras, India</json:string></affiliations></json:item><json:item><name>Bernhard Steffen</name><affiliations><json:string>University of Dortmund, Dortmund, Germany</json:string></affiliations></json:item><json:item><name>Madhu Sudan</name><affiliations><json:string>Massachusetts Institute of Technology, MA, USA</json:string></affiliations></json:item><json:item><name>Demetri Terzopoulos</name><affiliations><json:string>University of California, Los Angeles, CA, USA</json:string></affiliations></json:item><json:item><name>Doug Tygar</name><affiliations><json:string>University of California, Berkeley, CA, USA</json:string></affiliations></json:item><json:item><name>Moshe Y. Vardi</name><affiliations><json:string>Rice University, Houston, TX, USA</json:string></affiliations></json:item><json:item><name>Gerhard Weikum</name><affiliations><json:string>Max-Planck Institute of Computer Science, Saarbrücken, Germany</json:string></affiliations></json:item></author></serie><host><title>Computer Vision – ECCV 2010</title><language><json:string>unknown</json:string></language><copyrightDate>2010</copyrightDate><doi><json:string>10.1007/978-3-642-15549-9</json:string></doi><issn><json:string>0302-9743</json:string></issn><eissn><json:string>1611-3349</json:string></eissn><eisbn><json:string>978-3-642-15549-9</json:string></eisbn><bookId><json:string>978-3-642-15549-9</json:string></bookId><isbn><json:string>978-3-642-15548-2</json:string></isbn><volume>6311</volume><pages><first>734</first><last>747</last></pages><genre><json:string>book-series</json:string></genre><editor><json:item><name>Kostas Daniilidis</name><affiliations><json:string>GRASP Laboratory, University of Pennsylvania, 3330 Walnut Street, 19104, Philadelphia, PA, USA</json:string><json:string>E-mail: kostas@cis.upenn.edu</json:string></affiliations></json:item><json:item><name>Petros Maragos</name><affiliations><json:string>School of Electrical and Computer Engineering, National Technical University of Athens, 15773, Athens, Greece</json:string><json:string>E-mail: maragos@cs.ntua.gr</json:string></affiliations></json:item><json:item><name>Nikos Paragios</name><affiliations><json:string>Department of Applied Mathematics, Ecole Centrale de Paris, Grande Voie des Vignes, 92295, Chatenay-Malabry, France</json:string><json:string>E-mail: nikos.paragios@ecp.fr</json:string></affiliations></json:item></editor><subject><json:item><value>Computer Science</value></json:item><json:item><value>Computer Science</value></json:item><json:item><value>Computer Imaging, Vision, Pattern Recognition and Graphics</value></json:item><json:item><value>Image Processing and Computer Vision</value></json:item><json:item><value>Pattern Recognition</value></json:item><json:item><value>Biometrics</value></json:item><json:item><value>Computer Graphics</value></json:item><json:item><value>Algorithm Analysis and Problem Complexity</value></json:item></subject></host><ark><json:string>ark:/67375/HCB-BC0JQ01W-G</json:string></ark><publicationDate>2010</publicationDate><copyrightDate>2010</copyrightDate><doi><json:string>10.1007/978-3-642-15549-9_53</json:string></doi><id>F010BB5C335677A88726C68AF0EC082316831FF3</id><score>1</score><fulltext><json:item><extension>pdf</extension><original>true</original><mimetype>application/pdf</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-BC0JQ01W-G/fulltext.pdf</uri></json:item><json:item><extension>zip</extension><original>false</original><mimetype>application/zip</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-BC0JQ01W-G/bundle.zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/ark:/67375/HCB-BC0JQ01W-G/fulltext.tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title></titleStmt><publicationStmt><authority>ISTEX</authority><availability><licence>Springer-Verlag Berlin Heidelberg</licence></availability><date when="2010">2010</date></publicationStmt><notesStmt><note type="conference" source="proceedings" scheme="https://content-type.data.istex.fr/ark:/67375/XTP-BFHXPBJJ-3">conference</note><note type="publication-type" subtype="book-series" scheme="https://publication-type.data.istex.fr/ark:/67375/JMC-0G6R5W5T-Z">book-series</note></notesStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title><author><persName><forename type="first">Stephan</forename><surname>Gammeter</surname></persName><email>gammeter@vision.ee.ethz.ch</email><affiliation><orgName type="department">BIWI</orgName><orgName type="institution">ETH Zürich</orgName><address><country key=""></country></address></affiliation></author><author><persName><forename type="first">Till</forename><surname>Quack</surname></persName><email>tquack@vision.ee.ethz.ch</email><affiliation><orgName type="department">BIWI</orgName><orgName type="institution">ETH Zürich</orgName><address><country key=""></country></address></affiliation></author><author><persName><forename type="first">David</forename><surname>Tingdahl</surname></persName><email>david.tingdahl@esat.kuleuven.be</email><affiliation><orgName type="department">VISICS</orgName><orgName type="institution">K.U. Leuven</orgName><address><country key=""></country></address></affiliation></author><author><persName><forename type="first">Luc</forename><nameLink>van</nameLink><surname>Gool</surname></persName><email>vangool@vision.ee.ethz.ch</email><affiliation><orgName type="department">BIWI</orgName><orgName type="institution">ETH Zürich</orgName><address><country key=""></country></address></affiliation><affiliation><orgName type="department">VISICS</orgName><orgName type="institution">K.U. Leuven</orgName><address><country key=""></country></address></affiliation></author><idno type="istex">F010BB5C335677A88726C68AF0EC082316831FF3</idno><idno type="ark">ark:/67375/HCB-BC0JQ01W-G</idno><idno type="DOI">10.1007/978-3-642-15549-9_53</idno></analytic><monogr><title level="m" type="main">Computer Vision – ECCV 2010</title><title level="m" type="sub">11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I</title><title level="m" type="part">Spotlights and Posters M2</title><idno type="DOI">10.1007/978-3-642-15549-9</idno><idno type="book-id">978-3-642-15549-9</idno><idno type="ISBN">978-3-642-15548-2</idno><idno type="eISBN">978-3-642-15549-9</idno><idno type="chapter-id">Chap53</idno><idno type="part-id">Part3</idno><editor><persName><forename type="first">Kostas</forename><surname>Daniilidis</surname></persName><email>kostas@cis.upenn.edu</email><affiliation><orgName type="department">GRASP Laboratory</orgName><orgName type="institution">University of Pennsylvania</orgName><address><street>3330 Walnut Street</street><postCode>19104</postCode><settlement>Philadelphia</settlement><region>PA</region><country key="US">UNITED STATES</country></address></affiliation></editor><editor><persName><forename type="first">Petros</forename><surname>Maragos</surname></persName><email>maragos@cs.ntua.gr</email><affiliation><orgName type="department">School of Electrical and Computer Engineering</orgName><orgName type="institution">National Technical University of Athens</orgName><address><postCode>15773</postCode><settlement>Athens</settlement><country key="GR">GREECE</country></address></affiliation></editor><editor><persName><forename type="first">Nikos</forename><surname>Paragios</surname></persName><email>nikos.paragios@ecp.fr</email><affiliation><orgName type="department">Department of Applied Mathematics</orgName><orgName type="institution">Ecole Centrale de Paris</orgName><address><street>Grande Voie des Vignes</street><postCode>92295</postCode><settlement>Chatenay-Malabry</settlement><country key="FR">FRANCE</country></address></affiliation></editor><imprint><biblScope unit="vol">6311</biblScope><biblScope unit="page" from="734">734</biblScope><biblScope unit="page" to="747">747</biblScope><biblScope unit="chapter-count">57</biblScope><biblScope unit="part-chapter-count">13</biblScope></imprint></monogr><series><title level="s" type="main" xml:lang="en">Lecture Notes in Computer Science</title><author><persName><forename type="first">David</forename><surname>Hutchison</surname></persName><affiliation><orgName type="institution">Lancaster University</orgName><address><settlement>Lancaster</settlement><country key="GB">UNITED KINGDOM</country></address></affiliation></author><author><persName><forename type="first">Takeo</forename><surname>Kanade</surname></persName><affiliation><orgName type="institution">Carnegie Mellon University</orgName><address><settlement>Pittsburgh</settlement><region>PA</region><country key="US">UNITED STATES</country></address></affiliation></author><author><persName><forename type="first">Josef</forename><surname>Kittler</surname></persName><affiliation><orgName type="institution">University of Surrey</orgName><address><settlement>Guildford</settlement><country key="GB">UNITED KINGDOM</country></address></affiliation></author><author><persName><forename type="first">Jon</forename><forename type="first">M.</forename><surname>Kleinberg</surname></persName><affiliation><orgName type="institution">Cornell University</orgName><address><settlement>Ithaca</settlement><region>NY</region><country key="US">UNITED STATES</country></address></affiliation></author><author><persName><forename type="first">Friedemann</forename><surname>Mattern</surname></persName><affiliation><orgName type="institution">ETH Zurich</orgName><address><settlement>Zurich</settlement><country key="CH">SWITZERLAND</country></address></affiliation></author><author><persName><forename type="first">John</forename><forename type="first">C.</forename><surname>Mitchell</surname></persName><affiliation><orgName type="institution">Stanford University</orgName><address><settlement>Stanford</settlement><region>CA</region><country key="US">UNITED STATES</country></address></affiliation></author><author><persName><forename type="first">Moni</forename><surname>Naor</surname></persName><affiliation><orgName type="institution">Weizmann Institute of Science</orgName><address><settlement>Rehovot</settlement><country key="IL">ISRAEL</country></address></affiliation></author><author><persName><forename type="first">Oscar</forename><surname>Nierstrasz</surname></persName><affiliation><orgName type="institution">University of Bern</orgName><address><settlement>Bern</settlement><country key="CH">SWITZERLAND</country></address></affiliation></author><author><persName><forename type="first">C.</forename><surname>Pandu Rangan</surname></persName><affiliation><orgName type="institution">Indian Institute of Technology</orgName><address><settlement>Madras</settlement><country key="IN">INDIA</country></address></affiliation></author><author><persName><forename type="first">Bernhard</forename><surname>Steffen</surname></persName><affiliation><orgName type="institution">University of Dortmund</orgName><address><settlement>Dortmund</settlement><country key="DE">GERMANY</country></address></affiliation></author><author><persName><forename type="first">Madhu</forename><surname>Sudan</surname></persName><affiliation><orgName type="institution">Massachusetts Institute of Technology</orgName><address><region>MA</region><country key="US">UNITED STATES</country></address></affiliation></author><author><persName><forename type="first">Demetri</forename><surname>Terzopoulos</surname></persName><affiliation><orgName type="institution">University of California</orgName><address><settlement>Los Angeles</settlement><region>CA</region><country key="US">UNITED STATES</country></address></affiliation></author><author><persName><forename type="first">Doug</forename><surname>Tygar</surname></persName><affiliation><orgName type="institution">University of California</orgName><address><settlement>Berkeley</settlement><region>CA</region><country key="US">UNITED STATES</country></address></affiliation></author><author><persName><forename type="first">Moshe</forename><forename type="first">Y.</forename><surname>Vardi</surname></persName><affiliation><orgName type="institution">Rice University</orgName><address><settlement>Houston</settlement><region>TX</region><country key="US">UNITED STATES</country></address></affiliation></author><author><persName><forename type="first">Gerhard</forename><surname>Weikum</surname></persName><affiliation><orgName type="institution">Max-Planck Institute of Computer Science</orgName><address><settlement>Saarbrücken</settlement><country key="DE">GERMANY</country></address></affiliation></author><idno type="pISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="seriesID">558</idno></series></biblStruct></sourceDesc></fileDesc><profileDesc><abstract xml:lang="en"><head>Abstract</head><p>Most of the recent work on image-based object recognition and 3D reconstruction has focused on improving the underlying algorithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also affects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clusters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make object recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Furthermore, the methods are completely data-driven and fully automatic.</p></abstract><textClass ana="subject"><keywords scheme="book-subject-collection"><list><label>SUCO11645</label><item><term>Computer Science</term></item></list></keywords></textClass><textClass ana="subject"><keywords scheme="book-subject"><list><label>I</label><item><term type="Primary">Computer Science</term></item><label>I22005</label><item><term type="Secondary" subtype="priority-1">Computer Imaging, Vision, Pattern Recognition and Graphics</term></item><label>I22021</label><item><term type="Secondary" subtype="priority-2">Image Processing and Computer Vision</term></item><label>I2203X</label><item><term type="Secondary" subtype="priority-3">Pattern Recognition</term></item><label>I22040</label><item><term type="Secondary" subtype="priority-4">Biometrics</term></item><label>I22013</label><item><term type="Secondary" subtype="priority-5">Computer Graphics</term></item><label>I16021</label><item><term type="Secondary" subtype="priority-6">Algorithm Analysis and Problem Complexity</term></item></list></keywords></textClass><langUsage><language ident="EN"></language></langUsage></profileDesc></teiHeader></istex:fulltextTEI><json:item><extension>txt</extension><original>false</original><mimetype>text/plain</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-BC0JQ01W-G/fulltext.txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="corpus springer-ebooks not found" wicri:toSee="no header"><istex:xmlDeclaration>version="1.0" encoding="UTF-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//Springer-Verlag//DTD A++ V2.4//EN" URI="http://devel.springer.de/A++/V2.4/DTD/A++V2.4.dtd" name="istex:docType"></istex:docType><istex:document><Publisher><PublisherInfo><PublisherName>Springer Berlin Heidelberg</PublisherName><PublisherLocation>Berlin, Heidelberg</PublisherLocation></PublisherInfo><Series><SeriesInfo SeriesType="Series" TocLevels="0"><SeriesID>558</SeriesID><SeriesPrintISSN>0302-9743</SeriesPrintISSN><SeriesElectronicISSN>1611-3349</SeriesElectronicISSN><SeriesTitle Language="En">Lecture Notes in Computer Science</SeriesTitle></SeriesInfo><SeriesHeader><AuthorGroup><Author AffiliationIDS="Aff1"><AuthorName DisplayOrder="Western"><GivenName>David</GivenName><FamilyName>Hutchison</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff2"><AuthorName DisplayOrder="Western"><GivenName>Takeo</GivenName><FamilyName>Kanade</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff3"><AuthorName DisplayOrder="Western"><GivenName>Josef</GivenName><FamilyName>Kittler</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff4"><AuthorName DisplayOrder="Western"><GivenName>Jon</GivenName><GivenName>M.</GivenName><FamilyName>Kleinberg</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff5"><AuthorName DisplayOrder="Western"><GivenName>Friedemann</GivenName><FamilyName>Mattern</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff6"><AuthorName DisplayOrder="Western"><GivenName>John</GivenName><GivenName>C.</GivenName><FamilyName>Mitchell</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff7"><AuthorName DisplayOrder="Western"><GivenName>Moni</GivenName><FamilyName>Naor</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff8"><AuthorName DisplayOrder="Western"><GivenName>Oscar</GivenName><FamilyName>Nierstrasz</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff9"><AuthorName DisplayOrder="Western"><GivenName>C.</GivenName><FamilyName>Pandu Rangan</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff10"><AuthorName DisplayOrder="Western"><GivenName>Bernhard</GivenName><FamilyName>Steffen</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff11"><AuthorName DisplayOrder="Western"><GivenName>Madhu</GivenName><FamilyName>Sudan</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff12"><AuthorName DisplayOrder="Western"><GivenName>Demetri</GivenName><FamilyName>Terzopoulos</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff13"><AuthorName DisplayOrder="Western"><GivenName>Doug</GivenName><FamilyName>Tygar</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff14"><AuthorName DisplayOrder="Western"><GivenName>Moshe</GivenName><GivenName>Y.</GivenName><FamilyName>Vardi</FamilyName></AuthorName></Author><Author AffiliationIDS="Aff15"><AuthorName DisplayOrder="Western"><GivenName>Gerhard</GivenName><FamilyName>Weikum</FamilyName></AuthorName></Author><Affiliation ID="Aff1"><OrgName>Lancaster University</OrgName><OrgAddress><City>Lancaster</City><Country>UK</Country></OrgAddress></Affiliation><Affiliation ID="Aff2"><OrgName>Carnegie Mellon University</OrgName><OrgAddress><City>Pittsburgh</City><State>PA</State><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff3"><OrgName>University of Surrey</OrgName><OrgAddress><City>Guildford</City><Country>UK</Country></OrgAddress></Affiliation><Affiliation ID="Aff4"><OrgName>Cornell University</OrgName><OrgAddress><City>Ithaca</City><State>NY</State><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff5"><OrgName>ETH Zurich</OrgName><OrgAddress><City>Zurich</City><Country>Switzerland</Country></OrgAddress></Affiliation><Affiliation ID="Aff6"><OrgName>Stanford University</OrgName><OrgAddress><City>Stanford</City><State>CA</State><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff7"><OrgName>Weizmann Institute of Science</OrgName><OrgAddress><City>Rehovot</City><Country>Israel</Country></OrgAddress></Affiliation><Affiliation ID="Aff8"><OrgName>University of Bern</OrgName><OrgAddress><City>Bern</City><Country>Switzerland</Country></OrgAddress></Affiliation><Affiliation ID="Aff9"><OrgName>Indian Institute of Technology</OrgName><OrgAddress><City>Madras</City><Country>India</Country></OrgAddress></Affiliation><Affiliation ID="Aff10"><OrgName>University of Dortmund</OrgName><OrgAddress><City>Dortmund</City><Country>Germany</Country></OrgAddress></Affiliation><Affiliation ID="Aff11"><OrgName>Massachusetts Institute of Technology</OrgName><OrgAddress><State>MA</State><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff12"><OrgName>University of California</OrgName><OrgAddress><City>Los Angeles</City><State>CA</State><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff13"><OrgName>University of California</OrgName><OrgAddress><City>Berkeley</City><State>CA</State><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff14"><OrgName>Rice University</OrgName><OrgAddress><City>Houston</City><State>TX</State><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff15"><OrgName>Max-Planck Institute of Computer Science</OrgName><OrgAddress><City>Saarbrücken</City><Country>Germany</Country></OrgAddress></Affiliation></AuthorGroup></SeriesHeader><Book Language="En"><BookInfo BookProductType="Proceedings" ContainsESM="No" Language="En" MediaType="eBook" NumberingDepth="2" NumberingStyle="ContentOnly" OutputMedium="All" TocLevels="0"><BookID>978-3-642-15549-9</BookID><BookTitle>Computer Vision – ECCV 2010</BookTitle><BookSubTitle>11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I</BookSubTitle><BookVolumeNumber>6311</BookVolumeNumber><BookSequenceNumber>6311</BookSequenceNumber><BookDOI>10.1007/978-3-642-15549-9</BookDOI><BookTitleID>213329</BookTitleID><BookPrintISBN>978-3-642-15548-2</BookPrintISBN><BookElectronicISBN>978-3-642-15549-9</BookElectronicISBN><BookChapterCount>57</BookChapterCount><BookCopyright><CopyrightHolderName>Springer-Verlag Berlin Heidelberg</CopyrightHolderName><CopyrightYear>2010</CopyrightYear></BookCopyright><BookSubjectGroup><BookSubject Code="I" Type="Primary">Computer Science</BookSubject><BookSubject Code="I22005" Priority="1" Type="Secondary">Computer Imaging, Vision, Pattern Recognition and Graphics</BookSubject><BookSubject Code="I22021" Priority="2" Type="Secondary">Image Processing and Computer Vision</BookSubject><BookSubject Code="I2203X" Priority="3" Type="Secondary">Pattern Recognition</BookSubject><BookSubject Code="I22040" Priority="4" Type="Secondary">Biometrics</BookSubject><BookSubject Code="I22013" Priority="5" Type="Secondary">Computer Graphics</BookSubject><BookSubject Code="I16021" Priority="6" Type="Secondary">Algorithm Analysis and Problem Complexity</BookSubject><SubjectCollection Code="SUCO11645">Computer Science</SubjectCollection></BookSubjectGroup><BookContext><SeriesID>558</SeriesID></BookContext></BookInfo><BookHeader><EditorGroup><Editor AffiliationIDS="Aff16"><EditorName DisplayOrder="Western"><GivenName>Kostas</GivenName><FamilyName>Daniilidis</FamilyName></EditorName><Contact><Email>kostas@cis.upenn.edu</Email></Contact></Editor><Editor AffiliationIDS="Aff17"><EditorName DisplayOrder="Western"><GivenName>Petros</GivenName><FamilyName>Maragos</FamilyName></EditorName><Contact><Email>maragos@cs.ntua.gr</Email></Contact></Editor><Editor AffiliationIDS="Aff18"><EditorName DisplayOrder="Western"><GivenName>Nikos</GivenName><FamilyName>Paragios</FamilyName></EditorName><Contact><Email>nikos.paragios@ecp.fr</Email></Contact></Editor><Affiliation ID="Aff16"><OrgDivision>GRASP Laboratory</OrgDivision><OrgName>University of Pennsylvania</OrgName><OrgAddress><Street>3330 Walnut Street</Street><Postcode>19104</Postcode><City>Philadelphia</City><State>PA</State><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff17"><OrgDivision>School of Electrical and Computer Engineering</OrgDivision><OrgName>National Technical University of Athens</OrgName><OrgAddress><Postcode>15773</Postcode><City>Athens</City><Country>Greece</Country></OrgAddress></Affiliation><Affiliation ID="Aff18"><OrgDivision>Department of Applied Mathematics</OrgDivision><OrgName>Ecole Centrale de Paris</OrgName><OrgAddress><Street>Grande Voie des Vignes</Street><Postcode>92295</Postcode><City>Chatenay-Malabry</City><Country>France</Country></OrgAddress></Affiliation></EditorGroup></BookHeader><Part ID="Part3"><PartInfo TocLevels="0"><PartID>3</PartID><PartSequenceNumber>3</PartSequenceNumber><PartTitle>Spotlights and Posters M2</PartTitle><PartChapterCount>13</PartChapterCount><PartContext><SeriesID>558</SeriesID><BookTitle>Computer Vision – ECCV 2010</BookTitle></PartContext></PartInfo><Chapter ID="Chap53" Language="En"><ChapterInfo ChapterType="OriginalPaper" ContainsESM="No" NumberingDepth="2" NumberingStyle="ContentOnly" TocLevels="0"><ChapterID>53</ChapterID><ChapterDOI>10.1007/978-3-642-15549-9_53</ChapterDOI><ChapterSequenceNumber>53</ChapterSequenceNumber><ChapterTitle Language="En">Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</ChapterTitle><ChapterFirstPage>734</ChapterFirstPage><ChapterLastPage>747</ChapterLastPage><ChapterCopyright><CopyrightHolderName>Springer-Verlag Berlin Heidelberg</CopyrightHolderName><CopyrightYear>2010</CopyrightYear></ChapterCopyright><ChapterGrants Type="Regular"><MetadataGrant Grant="OpenAccess"></MetadataGrant><AbstractGrant Grant="OpenAccess"></AbstractGrant><BodyPDFGrant Grant="Restricted"></BodyPDFGrant><BodyHTMLGrant Grant="Restricted"></BodyHTMLGrant><BibliographyGrant Grant="Restricted"></BibliographyGrant><ESMGrant Grant="Restricted"></ESMGrant></ChapterGrants><ChapterContext><SeriesID>558</SeriesID><PartID>3</PartID><BookID>978-3-642-15549-9</BookID><BookTitle>Computer Vision – ECCV 2010</BookTitle></ChapterContext></ChapterInfo><ChapterHeader><AuthorGroup><Author AffiliationIDS="Aff19"><AuthorName DisplayOrder="Western"><GivenName>Stephan</GivenName><FamilyName>Gammeter</FamilyName></AuthorName><Contact><Email>gammeter@vision.ee.ethz.ch</Email><URL>http://www.vision.ee.ethz.ch</URL></Contact></Author><Author AffiliationIDS="Aff19"><AuthorName DisplayOrder="Western"><GivenName>Till</GivenName><FamilyName>Quack</FamilyName></AuthorName><Contact><Email>tquack@vision.ee.ethz.ch</Email><URL>http://www.vision.ee.ethz.ch</URL></Contact></Author><Author AffiliationIDS="Aff20"><AuthorName DisplayOrder="Western"><GivenName>David</GivenName><FamilyName>Tingdahl</FamilyName></AuthorName><Contact><Email>david.tingdahl@esat.kuleuven.be</Email><URL>http://www.esat.kuleuven.be/psi/visics</URL></Contact></Author><Author AffiliationIDS="Aff19 Aff20"><AuthorName DisplayOrder="Western"><GivenName>Luc</GivenName><Particle>van</Particle><FamilyName>Gool</FamilyName></AuthorName><Contact><Email>vangool@vision.ee.ethz.ch</Email><URL>http://www.esat.kuleuven.be/psi/visics</URL></Contact></Author><Affiliation ID="Aff19"><OrgDivision>BIWI</OrgDivision><OrgName>ETH Zürich</OrgName><OrgAddress><Country> </Country></OrgAddress></Affiliation><Affiliation ID="Aff20"><OrgDivision>VISICS</OrgDivision><OrgName>K.U. Leuven</OrgName><OrgAddress><Country> </Country></OrgAddress></Affiliation></AuthorGroup><Abstract ID="Abs1" Language="En"><Heading>Abstract</Heading><Para>Most of the recent work on image-based object recognition and 3D reconstruction has focused on improving the underlying algorithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also affects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clusters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make object recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Furthermore, the methods are completely data-driven and fully automatic.</Para></Abstract></ChapterHeader><NoBody></NoBody></Chapter></Part></Book></Series></Publisher></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title></titleInfo><titleInfo type="alternative" contentType="CDATA"><title>Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title></titleInfo><name type="personal"><namePart type="given">Stephan</namePart><namePart type="family">Gammeter</namePart><affiliation>BIWI, ETH Zürich, </affiliation><affiliation>E-mail: gammeter@vision.ee.ethz.ch</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Till</namePart><namePart type="family">Quack</namePart><affiliation>BIWI, ETH Zürich, </affiliation><affiliation>E-mail: tquack@vision.ee.ethz.ch</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">David</namePart><namePart type="family">Tingdahl</namePart><affiliation>VISICS, K.U. Leuven, </affiliation><affiliation>E-mail: david.tingdahl@esat.kuleuven.be</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Luc</namePart><namePart type="family">van Gool</namePart><affiliation>BIWI, ETH Zürich, </affiliation><affiliation>VISICS, K.U. Leuven, </affiliation><affiliation>E-mail: vangool@vision.ee.ethz.ch</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre displayLabel="OriginalPaper" authority="ISTEX" authorityURI="https://content-type.data.istex.fr" type="conference" valueURI="https://content-type.data.istex.fr/ark:/67375/XTP-BFHXPBJJ-3">conference</genre><originInfo><publisher>Springer Berlin Heidelberg</publisher><place><placeTerm type="text">Berlin, Heidelberg</placeTerm></place><dateIssued encoding="w3cdtf">2010</dateIssued><copyrightDate encoding="w3cdtf">2010</copyrightDate></originInfo><language><languageTerm type="code" authority="rfc3066">en</languageTerm><languageTerm type="code" authority="iso639-2b">eng</languageTerm></language><abstract lang="en">Abstract: Most of the recent work on image-based object recognition and 3D reconstruction has focused on improving the underlying algorithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also affects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clusters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make object recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Furthermore, the methods are completely data-driven and fully automatic.</abstract><relatedItem type="host"><titleInfo><title>Computer Vision – ECCV 2010</title><subTitle>11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I</subTitle></titleInfo><name type="personal"><namePart type="given">Kostas</namePart><namePart type="family">Daniilidis</namePart><affiliation>GRASP Laboratory, University of Pennsylvania, 3330 Walnut Street, 19104, Philadelphia, PA, USA</affiliation><affiliation>E-mail: kostas@cis.upenn.edu</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><name type="personal"><namePart type="given">Petros</namePart><namePart type="family">Maragos</namePart><affiliation>School of Electrical and Computer Engineering, National Technical University of Athens, 15773, Athens, Greece</affiliation><affiliation>E-mail: maragos@cs.ntua.gr</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><name type="personal"><namePart type="given">Nikos</namePart><namePart type="family">Paragios</namePart><affiliation>Department of Applied Mathematics, Ecole Centrale de Paris, Grande Voie des Vignes, 92295, Chatenay-Malabry, France</affiliation><affiliation>E-mail: nikos.paragios@ecp.fr</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><genre type="book-series" authority="ISTEX" authorityURI="https://publication-type.data.istex.fr" valueURI="https://publication-type.data.istex.fr/ark:/67375/JMC-0G6R5W5T-Z">book-series</genre><originInfo><publisher>Springer</publisher><copyrightDate encoding="w3cdtf">2010</copyrightDate><issuance>monographic</issuance></originInfo><subject><genre>Book-Subject-Collection</genre><topic authority="SpringerSubjectCodes" authorityURI="SUCO11645">Computer Science</topic></subject><subject><genre>Book-Subject-Group</genre><topic authority="SpringerSubjectCodes" authorityURI="I">Computer Science</topic><topic authority="SpringerSubjectCodes" authorityURI="I22005">Computer Imaging, Vision, Pattern Recognition and Graphics</topic><topic authority="SpringerSubjectCodes" authorityURI="I22021">Image Processing and Computer Vision</topic><topic authority="SpringerSubjectCodes" authorityURI="I2203X">Pattern Recognition</topic><topic authority="SpringerSubjectCodes" authorityURI="I22040">Biometrics</topic><topic authority="SpringerSubjectCodes" authorityURI="I22013">Computer Graphics</topic><topic authority="SpringerSubjectCodes" authorityURI="I16021">Algorithm Analysis and Problem Complexity</topic></subject><identifier type="DOI">10.1007/978-3-642-15549-9</identifier><identifier type="ISBN">978-3-642-15548-2</identifier><identifier type="eISBN">978-3-642-15549-9</identifier><identifier type="ISSN">0302-9743</identifier><identifier type="eISSN">1611-3349</identifier><identifier type="BookTitleID">213329</identifier><identifier type="BookID">978-3-642-15549-9</identifier><identifier type="BookChapterCount">57</identifier><identifier type="BookVolumeNumber">6311</identifier><identifier type="BookSequenceNumber">6311</identifier><identifier type="PartChapterCount">13</identifier><part><date>2010</date><detail type="part"><title>Spotlights and Posters M2</title></detail><detail type="volume"><number>6311</number><caption>vol.</caption></detail><extent unit="pages"><start>734</start><end>747</end></extent></part><recordInfo><recordOrigin>Springer-Verlag Berlin Heidelberg, 2010</recordOrigin></recordInfo></relatedItem><relatedItem type="series"><titleInfo><title>Lecture Notes in Computer Science</title></titleInfo><name type="personal"><namePart type="given">David</namePart><namePart type="family">Hutchison</namePart><affiliation>Lancaster University, Lancaster, UK</affiliation></name><name type="personal"><namePart type="given">Takeo</namePart><namePart type="family">Kanade</namePart><affiliation>Carnegie Mellon University, Pittsburgh, PA, USA</affiliation></name><name type="personal"><namePart type="given">Josef</namePart><namePart type="family">Kittler</namePart><affiliation>University of Surrey, Guildford, UK</affiliation></name><name type="personal"><namePart type="given">Jon</namePart><namePart type="given">M.</namePart><namePart type="family">Kleinberg</namePart><affiliation>Cornell University, Ithaca, NY, USA</affiliation></name><name type="personal"><namePart type="given">Friedemann</namePart><namePart type="family">Mattern</namePart><affiliation>ETH Zurich, Zurich, Switzerland</affiliation></name><name type="personal"><namePart type="given">John</namePart><namePart type="given">C.</namePart><namePart type="family">Mitchell</namePart><affiliation>Stanford University, Stanford, CA, USA</affiliation></name><name type="personal"><namePart type="given">Moni</namePart><namePart type="family">Naor</namePart><affiliation>Weizmann Institute of Science, Rehovot, Israel</affiliation></name><name type="personal"><namePart type="given">Oscar</namePart><namePart type="family">Nierstrasz</namePart><affiliation>University of Bern, Bern, Switzerland</affiliation></name><name type="personal"><namePart type="given">C.</namePart><namePart type="family">Pandu Rangan</namePart><affiliation>Indian Institute of Technology, Madras, India</affiliation></name><name type="personal"><namePart type="given">Bernhard</namePart><namePart type="family">Steffen</namePart><affiliation>University of Dortmund, Dortmund, Germany</affiliation></name><name type="personal"><namePart type="given">Madhu</namePart><namePart type="family">Sudan</namePart><affiliation>Massachusetts Institute of Technology, MA, USA</affiliation></name><name type="personal"><namePart type="given">Demetri</namePart><namePart type="family">Terzopoulos</namePart><affiliation>University of California, Los Angeles, CA, USA</affiliation></name><name type="personal"><namePart type="given">Doug</namePart><namePart type="family">Tygar</namePart><affiliation>University of California, Berkeley, CA, USA</affiliation></name><name type="personal"><namePart type="given">Moshe</namePart><namePart type="given">Y.</namePart><namePart type="family">Vardi</namePart><affiliation>Rice University, Houston, TX, USA</affiliation></name><name type="personal"><namePart type="given">Gerhard</namePart><namePart type="family">Weikum</namePart><affiliation>Max-Planck Institute of Computer Science, Saarbrücken, Germany</affiliation></name><originInfo><publisher>Springer</publisher><copyrightDate encoding="w3cdtf">2010</copyrightDate><issuance>serial</issuance></originInfo><identifier type="ISSN">0302-9743</identifier><identifier type="eISSN">1611-3349</identifier><identifier type="SeriesID">558</identifier><recordInfo><recordOrigin>Springer-Verlag Berlin Heidelberg, 2010</recordOrigin></recordInfo></relatedItem><identifier type="istex">F010BB5C335677A88726C68AF0EC082316831FF3</identifier><identifier type="ark">ark:/67375/HCB-BC0JQ01W-G</identifier><identifier type="DOI">10.1007/978-3-642-15549-9_53</identifier><identifier type="ChapterID">53</identifier><identifier type="ChapterID">Chap53</identifier><accessCondition type="use and reproduction" contentType="copyright">Springer-Verlag Berlin Heidelberg, 2010</accessCondition><recordInfo><recordContentSource authority="ISTEX" authorityURI="https://loaded-corpus.data.istex.fr" valueURI="https://loaded-corpus.data.istex.fr/ark:/67375/XBH-RLRX46XW-4">springer</recordContentSource><recordOrigin>Springer-Verlag Berlin Heidelberg, 2010</recordOrigin></recordInfo></mods><json:item><extension>json</extension><original>false</original><mimetype>application/json</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-BC0JQ01W-G/record.json</uri></json:item></metadata></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Europe/France/explor/NotreDameDeParisV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000399 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000399 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Europe/France
|area= NotreDameDeParisV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:F010BB5C335677A88726C68AF0EC082316831FF3
|texte= Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters
}}
| This area was generated with Dilib version V0.6.33. |  |