{"id":"https://openalex.org/W2026524281","doi":"https://doi.org/10.1145/1290082.1290089","title":"Clustering near-duplicate images in large collections","display_name":"Clustering near-duplicate images in large collections","publication_year":2007,"publication_date":"2007-09-24","ids":{"openalex":"https://openalex.org/W2026524281","doi":"https://doi.org/10.1145/1290082.1290089","mag":"2026524281"},"language":"en","primary_location":{"id":"doi:10.1145/1290082.1290089","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1290082.1290089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international workshop on Workshop on multimedia information retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059612159","display_name":"Jun Jie Foo","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jun Jie Foo","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101502254","display_name":"Ranjan Sinha","orcid":"https://orcid.org/0000-0003-2485-8549"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ranjan Sinha","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia","University of Melbourne, Melbourne, Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia,","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8379,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.85944429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8511499166488647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7459684610366821},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.5182440280914307},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.49593862891197205},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4775291681289673},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4554533362388611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.453220009803772},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4279821515083313},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42147111892700195},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4135354459285736},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4133670926094055},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.33306267857551575}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8511499166488647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459684610366821},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.5182440280914307},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.49593862891197205},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4775291681289673},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4554533362388611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453220009803772},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4279821515083313},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42147111892700195},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4135354459285736},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4133670926094055},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.33306267857551575},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1290082.1290089","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1290082.1290089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international workshop on Workshop on multimedia information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.463.1676","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.463.1676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nichol.as/papers/Foo/Clustering near-duplicate images in large collections.pdf","raw_type":"text"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/32001","is_oa":false,"landing_page_url":"http://hdl.handle.net/11343/32001","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MM07: The 15th ACM International Conference on Multimedia 2007","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1515236863","https://openalex.org/W1536700701","https://openalex.org/W1677409904","https://openalex.org/W1967666795","https://openalex.org/W1980722661","https://openalex.org/W2027678432","https://openalex.org/W2055289292","https://openalex.org/W2106485656","https://openalex.org/W2111048828","https://openalex.org/W2118462228","https://openalex.org/W2124330204","https://openalex.org/W2129070169","https://openalex.org/W2129116707","https://openalex.org/W2130910507","https://openalex.org/W2131846894","https://openalex.org/W2132139375","https://openalex.org/W2138662031","https://openalex.org/W2145072179","https://openalex.org/W2147332957","https://openalex.org/W2147717514","https://openalex.org/W2148781362","https://openalex.org/W2151103935","https://openalex.org/W2152565070","https://openalex.org/W2171516284","https://openalex.org/W2172188317","https://openalex.org/W2172232203","https://openalex.org/W6629956336","https://openalex.org/W6685384759","https://openalex.org/W6733730882"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2622412490","https://openalex.org/W2406185607","https://openalex.org/W2067669858","https://openalex.org/W2311450085","https://openalex.org/W2118740473","https://openalex.org/W3168918549","https://openalex.org/W3197105638","https://openalex.org/W2077759297","https://openalex.org/W2473308841"],"abstract_inverted_index":{"Near-duplicate":[0],"images":[1],"introduce":[2],"problems":[3],"of":[4,22,26,45,55,65,85],"redundancy":[5],"and":[6,52],"copyright":[7],"infringement":[8],"in":[9],"large":[10],"image":[11,49,67],"collections.":[12],"The":[13],"problem":[14],"is":[15,28,80],"acute":[16],"on":[17,114],"the":[18,115],"web,":[19],"where":[20],"appropriation":[21],"im-ages":[23,113],"without":[24],"acknowledgment":[25],"source":[27],"prevalent.":[29],"In":[30],"this":[31,71],"paper,":[32],"we":[33,60],"present":[34],"an":[35,53],"effective":[36,82],"clustering":[37,58,72,78,111],"approach":[38,64,79,105],"for":[39,70,83,110],"near-duplicate":[40,56,66,112],"images,":[41],"using":[42],"a":[43,88,107],"combination":[44],"techniques":[46],"from":[47],"invariant":[48],"local":[50],"descriptors":[51],"adaptation":[54],"text-document":[57],"techniques;":[59],"extend":[61],"our":[62,77,104],"earlier":[63],"pairwise":[68],"iden-tification":[69],"approach.":[73],"We":[74,93],"demonstrate":[75],"that":[76,103],"highly":[81],"collections":[84],"up":[86],"to":[87],"few":[89],"hundred":[90],"thousand":[91],"images.":[92],"also":[94],"show":[95],"\u2014":[96,102],"via":[97],"experimentation":[98],"with":[99],"real":[100],"examples":[101],"presents":[106],"viable":[108],"solution":[109],"Web.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}