{"id":"https://openalex.org/W2112459890","doi":"https://doi.org/10.1145/2324796.2324798","title":"High-confidence near-duplicate image detection","display_name":"High-confidence near-duplicate image detection","publication_year":2012,"publication_date":"2012-06-05","ids":{"openalex":"https://openalex.org/W2112459890","doi":"https://doi.org/10.1145/2324796.2324798","mag":"2112459890"},"language":"en","primary_location":{"id":"doi:10.1145/2324796.2324798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","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/A5086692495","display_name":"Wei Dong","orcid":"https://orcid.org/0000-0003-3067-8720"},"institutions":[{"id":"https://openalex.org/I4210140958","display_name":"Ann Arbor Center for Independent Living","ror":"https://ror.org/045pcya52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140958"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Dong","raw_affiliation_strings":["Independent Researcher, Ann Arbor MI"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Ann Arbor MI","institution_ids":["https://openalex.org/I4210140958"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407602","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0002-1385-9012"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["Princeton University, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071016611","display_name":"Moses Charikar","orcid":"https://orcid.org/0000-0003-0807-3389"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moses Charikar","raw_affiliation_strings":["Princeton University, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100399952","display_name":"Kai Li","orcid":"https://orcid.org/0000-0002-8962-2644"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["Princeton University, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086692495"],"corresponding_institution_ids":["https://openalex.org/I4210140958"],"apc_list":null,"apc_paid":null,"fwci":4.3926,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.95255082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9934999942779541,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7627534866333008},{"id":"https://openalex.org/keywords/true-positive-rate","display_name":"True positive rate","score":0.647916316986084},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6197609901428223},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.6196337938308716},{"id":"https://openalex.org/keywords/scale-invariant-feature-transform","display_name":"Scale-invariant feature transform","score":0.6101672053337097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5440099239349365},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4689818024635315},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4547620415687561},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3884902596473694},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3708186149597168},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3383257985115051},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.12893736362457275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627534866333008},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.647916316986084},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6197609901428223},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.6196337938308716},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.6101672053337097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440099239349365},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4689818024635315},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4547620415687561},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3884902596473694},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3708186149597168},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3383257985115051},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.12893736362457275}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2324796.2324798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1976591483","https://openalex.org/W2012592962","https://openalex.org/W2020308406","https://openalex.org/W2029785729","https://openalex.org/W2045107949","https://openalex.org/W2055289292","https://openalex.org/W2066941820","https://openalex.org/W2067952552","https://openalex.org/W2086254934","https://openalex.org/W2100398441","https://openalex.org/W2107711468","https://openalex.org/W2128017662","https://openalex.org/W2133671054","https://openalex.org/W2141362318","https://openalex.org/W2145349611","https://openalex.org/W2147717514","https://openalex.org/W2148809531","https://openalex.org/W2151103935","https://openalex.org/W2154952031","https://openalex.org/W2166742463","https://openalex.org/W2170037597","https://openalex.org/W2172232203","https://openalex.org/W2293597654","https://openalex.org/W6697214482"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W3129715955","https://openalex.org/W4287692494","https://openalex.org/W3027053746","https://openalex.org/W3047594718","https://openalex.org/W4299651861","https://openalex.org/W2953243682","https://openalex.org/W4386222044","https://openalex.org/W2183246718","https://openalex.org/W2735955360"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,18,48],"propose":[4],"two":[5],"techniques":[6,102],"for":[7,56],"near-duplicate":[8],"image":[9,106],"detection":[10],"at":[11],"high":[12],"confidence":[13],"and":[14,34],"large":[15],"scale.":[16],"First,":[17],"show":[19,49,74],"that":[20,27,50,75],"entropy-based":[21],"filtering":[22],"eliminates":[23],"ambiguous":[24],"SIFT":[25],"features":[26],"cause":[28],"most":[29],"of":[30,42,89,122],"the":[31,43,93,100],"false":[32,85],"positives,":[33],"enables":[35],"claiming":[36],"near-duplicity":[37],"with":[38,59,71,78,103,116,130],"a":[39,60,104,117,131],"single":[40,132],"match":[41],"retained":[44],"high-quality":[45],"features.":[46],"Second,":[47],"graph":[51,62],"cut":[52],"can":[53],"be":[54],"used":[55],"query":[57],"expansion":[58],"duplicity":[61],"computed":[63,115],"offline":[64,114],"to":[65],"substantially":[66],"improve":[67],"search":[68,107],"quality.":[69],"Evaluation":[70],"web":[72,128],"images":[73,129],"when":[76],"combined":[77],"sketch":[79],"embedding":[80],"[6],":[81],"our":[82],"methods":[83],"achieve":[84],"positive":[86],"rate":[87],"orders":[88],"magnitude":[90],"lower":[91],"than":[92,125],"standard":[94],"visual":[95],"word":[96],"approach.":[97],"We":[98],"demonstrate":[99],"proposed":[101],"large-scale":[105],"engine":[108],"which,":[109],"using":[110],"indexing":[111],"data":[112],"structure":[113],"Hadoop":[118],"cluster,":[119],"is":[120],"capable":[121],"serving":[123],"more":[124],"50":[126],"million":[127],"commodity":[133],"server.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}