<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE rdf:RDF [
 <!ENTITY rdf 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'>
 <!ENTITY rdfs 'http://www.w3.org/2000/01/rdf-schema#'>

 <!ENTITY swrc 'http://swrc.ontoware.org/ontology#'>
 <!ENTITY xsd 'http://www.w3.org/2001/XMLSchema#'>
]>

<rdf:RDF
 xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
 xmlns="http://purl.org/rss/1.0/"
 xmlns:cc="http://web.resource.org/cc/"
 xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/"
 xmlns:dc="http://purl.org/dc/elements/1.1/"
 xmlns:syn="http://purl.org/rss/1.0/modules/syndication/"
 xmlns:content="http://purl.org/rss/1.0/modules/content/"
 xmlns:admin="http://webns.net/mvcb/"
 xmlns:burst="http://xmlns.com/burst/0.1/"
 
 xmlns:rdfs="&rdfs;"
 xmlns:swrc="&swrc;"
 xmlns:xsd="&xsd;"
>

<channel rdf:about="http://www.bibsonomy.org/uri/author/Wang/2003">
  <title>BibSonomy publications for /author/Wang/2003</title>
  <link>http://www.bibsonomy.org/burst/author/Wang/2003</link>
  <description>BibSonomy BuRST Feed for /author/Wang/2003</description>
  <dc:date>2008-07-27T03:03:32+02:00</dc:date>

  <items>
    <rdf:Seq>
      <rdf:li rdf:resource="http://www.bibsonomy.org/uri/bibtex/249793b7f5d767cc9b5df7b557b3d6781/seandalai"/>
      </rdf:Seq>
  </items>
</channel>

<item rdf:about="http://www.bibsonomy.org/uri/bibtex/249793b7f5d767cc9b5df7b557b3d6781/seandalai">
    <title>Bootstrapping SVM active learning by incorporating unlabelled images for image retrieval</title>
    <link>http://www.bibsonomy.org/bibtex/249793b7f5d767cc9b5df7b557b3d6781/seandalai</link>
    <dc:creator>seandalai</dc:creator>
    <dc:date>2007-02-17T01:58:15+01:00</dc:date>
    <dc:subject>2003 active image semi-supervised svm </dc:subject>
    <content:encoded>
	    <![CDATA[
        <div class="block">
	      <div class="bmtitle">

  <a href="http://www.bibsonomy.org/bibtex/249793b7f5d767cc9b5df7b557b3d6781/seandalai">Bootstrapping SVM active learning by incorporating unlabelled images for image retrieval</a>
</div>
<div class="bmdesc">
  <span style="color:#555555;"> 
    Lei <a href="http://www.bibsonomy.org/author/Wang">Wang</a>         	     	 
        	  and Kap Luk <a href="http://www.bibsonomy.org/author/Chan">Chan</a>         	     	 
        	  and Zhihua <a href="http://www.bibsonomy.org/author/Zhang">Zhang</a>         	     	 
        	 </span> 
  <em>IEEE Computer Society Conference on Computer Vision and Pattern Recognition</em>
    
  (2003)
</div>
<span class="bmmeta">
  
  
        to
        <span class="bmtags">
        <a href="http://www.bibsonomy.org/user/seandalai/2003">2003</a>
        <a href="http://www.bibsonomy.org/user/seandalai/active">active</a>
        <a href="http://www.bibsonomy.org/user/seandalai/image">image</a>
        <a href="http://www.bibsonomy.org/user/seandalai/semi-supervised">semi-supervised</a>
        <a href="http://www.bibsonomy.org/user/seandalai/svm">svm</a>
        </span>
        

          by <a href="http://www.bibsonomy.org/user/seandalai">seandalai</a> 
        
        
        on 2007-02-17 01:58:15 </span></div>
	    ]]>
    </content:encoded>
    <taxo:topics>
      <rdf:Bag>
        <rdf:li rdf:resource="http://www.bibsonomy.org/tag/2003" />
        <rdf:li rdf:resource="http://www.bibsonomy.org/tag/active" />
        <rdf:li rdf:resource="http://www.bibsonomy.org/tag/image" />
        <rdf:li rdf:resource="http://www.bibsonomy.org/tag/semi-supervised" />
        <rdf:li rdf:resource="http://www.bibsonomy.org/tag/svm" />
        </rdf:Bag>
    </taxo:topics>
    <burst:publication>
      <swrc:InProceedings>
        <swrc:booktitle>IEEE Computer Society Conference on Computer Vision and Pattern Recognition</swrc:booktitle><swrc:title>Bootstrapping SVM active learning by incorporating unlabelled images for image retrieval</swrc:title><swrc:year>2003</swrc:year><swrc:keywords>2003 active image semi-supervised svm </swrc:keywords><swrc:date>2007-02-17 01:58:15.0</swrc:date><swrc:abstract>The performance of image retrieval with SVM active learning is known to be poor when started with few labeled images only. In this paper, the problem is solved by incorporating the unlabelled images into the bootstrapping of the learning process. In this work, the initial SVM classifier is trained with the few labeled images and the unlabelled images randomly selected from the image database. Both theoretical analysis and experimental results show that by incorporating unlabelled images in the bootstrapping, the efficiency of SVM active learning can be improved, and thus improves the overall retrieval performance.</swrc:abstract><swrc:author>
  <rdf:Seq>
  <rdf:_1><swrc:Person swrc:name="Lei Wang" /></rdf:_1>
  <rdf:_2><swrc:Person swrc:name="Kap Luk Chan" /></rdf:_2>
  <rdf:_3><swrc:Person swrc:name="Zhihua Zhang" /></rdf:_3>
  </rdf:Seq>
</swrc:author>

<swrc:editor>
  <rdf:Seq>
  </rdf:Seq>
</swrc:editor></swrc:InProceedings>  
    </burst:publication>
  </item>
</rdf:RDF>