{"id":"https://openalex.org/W2171034893","doi":"https://doi.org/10.1109/tkde.2002.1019214","title":"Clustering for approximate similarity search in high-dimensional spaces","display_name":"Clustering for approximate similarity search in high-dimensional spaces","publication_year":2002,"publication_date":"2002-07-01","ids":{"openalex":"https://openalex.org/W2171034893","doi":"https://doi.org/10.1109/tkde.2002.1019214","mag":"2171034893"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2002.1019214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2002.1019214","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5100369916","display_name":"Chen Li","orcid":"https://orcid.org/0000-0003-1545-8885"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chen Li","raw_affiliation_strings":["Department of Computer Science, University of Stanford, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Stanford, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013545831","display_name":"Edward Yi Chang","orcid":"https://orcid.org/0000-0003-1616-5240"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Chang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055883336","display_name":"H\u00e9ctor Garc\u00eda-Molina","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Garcia-Molina","raw_affiliation_strings":["Department of Computer Science, University of Stanford, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Stanford, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108488081","display_name":"Gio Wiederhold","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Wiederhold","raw_affiliation_strings":["Department of Computer Science, University of Stanford, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Stanford, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100369916"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":9.5525,"has_fulltext":false,"cited_by_count":139,"citation_normalized_percentile":{"value":0.98709769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"4","first_page":"792","last_page":"808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9932000041007996,"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":0.817002534866333},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7806903123855591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554592490196228},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6281880140304565},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6021685004234314},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5767855048179626},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5624931454658508},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.48663291335105896},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.48484599590301514},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.482740581035614},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.48146310448646545},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4357350468635559},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3435860276222229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27617204189300537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19363027811050415}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.817002534866333},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7806903123855591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554592490196228},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6281880140304565},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6021685004234314},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5767855048179626},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5624931454658508},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.48663291335105896},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.48484599590301514},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.482740581035614},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.48146310448646545},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4357350468635559},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3435860276222229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27617204189300537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19363027811050415},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tkde.2002.1019214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2002.1019214","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.118.450","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.118.450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cchen1.csie.ntust.edu.tw/students/2009/clustering for approximate similarity search in high-dimensional spaces.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.295.5357","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.295.5357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infolab.stanford.edu/~echang/clindex.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.37.8077","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.37.8077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-db.stanford.edu/~echang/clindex.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1498561492","https://openalex.org/W1502916507","https://openalex.org/W1525103006","https://openalex.org/W1527659376","https://openalex.org/W1541459201","https://openalex.org/W1554663460","https://openalex.org/W1564100276","https://openalex.org/W1565494300","https://openalex.org/W1575476631","https://openalex.org/W1581687499","https://openalex.org/W1592090717","https://openalex.org/W1633659671","https://openalex.org/W1634005169","https://openalex.org/W1673310716","https://openalex.org/W1723433588","https://openalex.org/W1736005231","https://openalex.org/W1969357402","https://openalex.org/W1970319631","https://openalex.org/W1971238646","https://openalex.org/W1977496278","https://openalex.org/W1978447605","https://openalex.org/W2000830496","https://openalex.org/W2007842132","https://openalex.org/W2011549082","https://openalex.org/W2046144220","https://openalex.org/W2050749090","https://openalex.org/W2066610120","https://openalex.org/W2066799613","https://openalex.org/W2070572105","https://openalex.org/W2088101210","https://openalex.org/W2091503252","https://openalex.org/W2091718820","https://openalex.org/W2095897464","https://openalex.org/W2097042476","https://openalex.org/W2107627518","https://openalex.org/W2118269922","https://openalex.org/W2124330204","https://openalex.org/W2126626732","https://openalex.org/W2133542527","https://openalex.org/W2141044908","https://openalex.org/W2144679084","https://openalex.org/W2145725688","https://openalex.org/W2147717514","https://openalex.org/W2151135734","https://openalex.org/W2155776210","https://openalex.org/W2157092487","https://openalex.org/W2160066518","https://openalex.org/W2164162890","https://openalex.org/W2166239026","https://openalex.org/W2169351022","https://openalex.org/W2238624099","https://openalex.org/W2316478175","https://openalex.org/W2341204729","https://openalex.org/W2427881153","https://openalex.org/W2498094064","https://openalex.org/W2579555219","https://openalex.org/W2590799281","https://openalex.org/W2978337448","https://openalex.org/W2997027240","https://openalex.org/W3003570628","https://openalex.org/W3003734944","https://openalex.org/W3004909842","https://openalex.org/W3008251515","https://openalex.org/W3012615620","https://openalex.org/W4231029117","https://openalex.org/W4233485652","https://openalex.org/W4242599275","https://openalex.org/W4243869499","https://openalex.org/W4285719527","https://openalex.org/W4388297464","https://openalex.org/W6632397832","https://openalex.org/W6634394891","https://openalex.org/W6635595544","https://openalex.org/W6636873521","https://openalex.org/W7062905887"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2054476758","https://openalex.org/W1949910768","https://openalex.org/W1480566255","https://openalex.org/W2254397067","https://openalex.org/W2013685631","https://openalex.org/W1610355325","https://openalex.org/W1882921205","https://openalex.org/W2387801216"],"abstract_inverted_index":{"We":[0,86],"present":[1,100],"a":[2,33,42,79],"clustering":[3,92],"and":[4,62,93,99],"indexing":[5],"paradigm":[6],"(called":[7],"Clindex)":[8],"for":[9,17,84],"high-dimensional":[10],"search":[11],"spaces.":[12],"The":[13],"scheme":[14,50,70],"is":[15,71],"designed":[16],"approximate":[18],"similarity":[19],"searches,":[20,48],"where":[21,37],"one":[22,38],"would":[23],"like":[24],"to":[25],"find":[26,52],"many":[27],"of":[28],"the":[29,88],"data":[30],"points":[31,54],"near":[32,44,53],"target":[34],"point,":[35],"but":[36,81],"can":[39,51],"tolerate":[40],"missing":[41],"few":[43,60],"points.":[45],"For":[46],"such":[47,95],"our":[49],"with":[55],"high":[56],"recall":[57],"in":[58,91],"very":[59],"IOs":[61],"perform":[63],"significantly":[64],"better":[65],"than":[66],"other":[67],"approaches.":[68],"Our":[69],"based":[72],"on":[73],"finding":[74],"clusters":[75],"and,":[76],"then,":[77],"building":[78,94],"simple":[80],"efficient":[82],"index":[83,97],"them.":[85],"analyze":[87],"trade-offs":[89],"involved":[90],"an":[96],"structure,":[98],"extensive":[101],"experimental":[102],"results.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}