File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: Retrieving and ranking unannotated images through collaboratively mining online search results
  • Basic View
  • Metadata View
  • XML View
TitleRetrieving and ranking unannotated images through collaboratively mining online search results
 
AuthorsXu, S2
Jiang, H1
Lau, FCM1
 
KeywordsMultimedia information retrieval
Web information retrieval
Online reference image collection
Query processing
Retrieving unannotated images
Web search mining
 
Issue Date2011
 
PublisherAssociation for Computing Machinery.
 
CitationThe 20th ACM international conference on Information and knowledge management (CIKM 2011), Glasgow, Scotland, UK., 24-28 October 2011. In Proceedings of the 20th ACM CIKM, 2011, p. 485-494 [How to Cite?]
DOI: http://dx.doi.org/10.1145/2063576.2063650
 
AbstractWe present a new image search and ranking algorithm for retrieving unannotated images by collaboratively mining online search results which consist of online image and text search results. The online image search results are leveraged as reference examples to perform content-based image search over unannotated images. The online text search results are utilized to estimate the reference images' relevance to the search query. The key feature of our method is its capability to deal with unreliable online image search results through jointly mining visual and textual aspects of online search results. Through such collaborative mining, our algorithm infers the relevance of an online search result image to a text query. Once we obtain the estimate of query relevance score for each online image search result, we can selectively use query specific online search result images as reference examples for retrieving and ranking unannotated images. We tested our algorithm both on the standard public image datasets and several modestly sized personal photo collections. We also compared our method with two well-known peer methods. The results indicate that our algorithm is superior to existing content-based image search algorithms for retrieving and ranking unannotated images. © 2011 ACM.
 
ISBN978-1-4503-0717-8
 
DOIhttp://dx.doi.org/10.1145/2063576.2063650
 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorXu, S
 
dc.contributor.authorJiang, H
 
dc.contributor.authorLau, FCM
 
dc.date.accessioned2012-06-26T06:32:34Z
 
dc.date.available2012-06-26T06:32:34Z
 
dc.date.issued2011
 
dc.description.abstractWe present a new image search and ranking algorithm for retrieving unannotated images by collaboratively mining online search results which consist of online image and text search results. The online image search results are leveraged as reference examples to perform content-based image search over unannotated images. The online text search results are utilized to estimate the reference images' relevance to the search query. The key feature of our method is its capability to deal with unreliable online image search results through jointly mining visual and textual aspects of online search results. Through such collaborative mining, our algorithm infers the relevance of an online search result image to a text query. Once we obtain the estimate of query relevance score for each online image search result, we can selectively use query specific online search result images as reference examples for retrieving and ranking unannotated images. We tested our algorithm both on the standard public image datasets and several modestly sized personal photo collections. We also compared our method with two well-known peer methods. The results indicate that our algorithm is superior to existing content-based image search algorithms for retrieving and ranking unannotated images. © 2011 ACM.
 
dc.description.naturelink_to_OA_fulltext
 
dc.description.otherThe 20th ACM international conference on Information and knowledge management (CIKM 2011), Glasgow, Scotland, UK., 24-28 October 2011. In Proceedings of the 20th ACM CIKM, 2011, p. 485-494
 
dc.identifier.citationThe 20th ACM international conference on Information and knowledge management (CIKM 2011), Glasgow, Scotland, UK., 24-28 October 2011. In Proceedings of the 20th ACM CIKM, 2011, p. 485-494 [How to Cite?]
DOI: http://dx.doi.org/10.1145/2063576.2063650
 
dc.identifier.doihttp://dx.doi.org/10.1145/2063576.2063650
 
dc.identifier.epage494
 
dc.identifier.hkuros211544
 
dc.identifier.isbn978-1-4503-0717-8
 
dc.identifier.scopuseid_2-s2.0-83055191902
 
dc.identifier.spage485
 
dc.identifier.urihttp://hdl.handle.net/10722/152020
 
dc.languageeng
 
dc.publisherAssociation for Computing Machinery.
 
dc.publisher.placeUnited States
 
dc.relation.ispartofProceedings of the 20th ACM international conference on Information and knowledge management, CIKM 2011
 
dc.relation.referencesReferences in Scopus
 
dc.rightsProceedings of the 20th ACM international conference on Information and knowledge management, CIKM 2011. Copyright © Association for Computing Machinery.
 
dc.subjectMultimedia information retrieval
 
dc.subjectWeb information retrieval
 
dc.subjectOnline reference image collection
 
dc.subjectQuery processing
 
dc.subjectRetrieving unannotated images
 
dc.subjectWeb search mining
 
dc.titleRetrieving and ranking unannotated images through collaboratively mining online search results
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Xu, S</contributor.author>
<contributor.author>Jiang, H</contributor.author>
<contributor.author>Lau, FCM</contributor.author>
<date.accessioned>2012-06-26T06:32:34Z</date.accessioned>
<date.available>2012-06-26T06:32:34Z</date.available>
<date.issued>2011</date.issued>
<identifier.citation>The 20th ACM international conference on Information and knowledge management (CIKM 2011), Glasgow, Scotland, UK., 24-28 October 2011. In Proceedings of the 20th ACM CIKM, 2011, p. 485-494</identifier.citation>
<identifier.isbn>978-1-4503-0717-8</identifier.isbn>
<identifier.uri>http://hdl.handle.net/10722/152020</identifier.uri>
<description.abstract>We present a new image search and ranking algorithm for retrieving unannotated images by collaboratively mining online search results which consist of online image and text search results. The online image search results are leveraged as reference examples to perform content-based image search over unannotated images. The online text search results are utilized to estimate the reference images&apos; relevance to the search query. The key feature of our method is its capability to deal with unreliable online image search results through jointly mining visual and textual aspects of online search results. Through such collaborative mining, our algorithm infers the relevance of an online search result image to a text query. Once we obtain the estimate of query relevance score for each online image search result, we can selectively use query specific online search result images as reference examples for retrieving and ranking unannotated images. We tested our algorithm both on the standard public image datasets and several modestly sized personal photo collections. We also compared our method with two well-known peer methods. The results indicate that our algorithm is superior to existing content-based image search algorithms for retrieving and ranking unannotated images. &#169; 2011 ACM.</description.abstract>
<language>eng</language>
<publisher>Association for Computing Machinery.</publisher>
<relation.ispartof>Proceedings of the 20th ACM international conference on Information and knowledge management, CIKM 2011</relation.ispartof>
<rights>Proceedings of the 20th ACM international conference on Information and knowledge management, CIKM 2011. Copyright &#169; Association for Computing Machinery.</rights>
<subject>Multimedia information retrieval</subject>
<subject>Web information retrieval</subject>
<subject>Online reference image collection</subject>
<subject>Query processing</subject>
<subject>Retrieving unannotated images</subject>
<subject>Web search mining</subject>
<title>Retrieving and ranking unannotated images through collaboratively mining online search results</title>
<type>Conference_Paper</type>
<description.nature>link_to_OA_fulltext</description.nature>
<identifier.doi>10.1145/2063576.2063650</identifier.doi>
<identifier.scopus>eid_2-s2.0-83055191902</identifier.scopus>
<identifier.hkuros>211544</identifier.hkuros>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-83055191902&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<identifier.spage>485</identifier.spage>
<identifier.epage>494</identifier.epage>
<publisher.place>United States</publisher.place>
<description.other>The 20th ACM international conference on Information and knowledge management (CIKM 2011), Glasgow, Scotland, UK., 24-28 October 2011. In Proceedings of the 20th ACM CIKM, 2011, p. 485-494</description.other>
<bitstream.url>http://hub.hku.hk/bitstream/10722/152020/1/re01.htm</bitstream.url>
</item>
Author Affiliations
  1. The University of Hong Kong
  2. Oak Ridge National Laboratory