{"id":"https://openalex.org/W2345132233","doi":"https://doi.org/10.1109/tkde.2015.2506556","title":"Efficient Metric Indexing for Similarity Search and Similarity Joins","display_name":"Efficient Metric Indexing for Similarity Search and Similarity Joins","publication_year":2015,"publication_date":"2015-12-09","ids":{"openalex":"https://openalex.org/W2345132233","doi":"https://doi.org/10.1109/tkde.2015.2506556","mag":"2345132233"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2015.2506556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2015.2506556","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/A5100432093","display_name":"Lu Chen","orcid":"https://orcid.org/0000-0002-5685-7017"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Chen","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006238145","display_name":"Yunjun Gao","orcid":"https://orcid.org/0000-0003-3816-8450"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjun Gao","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China","Key Laboratory of Big Data Intelligent Computing of Zhejiang Province, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Key Laboratory of Big Data Intelligent Computing of Zhejiang Province, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011517305","display_name":"Xinhan Li","orcid":"https://orcid.org/0009-0002-6067-4683"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhan Li","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029380368","display_name":"Christian S. Jensen","orcid":"https://orcid.org/0000-0002-9697-7670"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Christian S. Jensen","raw_affiliation_strings":["Department of Computer Science, Aalborg University, Aalborg, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100389286","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-7483-0045"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China","Key Laboratory of Big Data Intelligent Computing of Zhejiang Province, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Key Laboratory of Big Data Intelligent Computing of Zhejiang Province, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100432093"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":3.1836,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.92866579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"29","issue":"3","first_page":"556","last_page":"571"},"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":0.9868999719619751,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9839000105857849,"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":0.7601650357246399},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7561901807785034},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6859118342399597},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6811205744743347},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5790554881095886},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5651508569717407},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5345221161842346},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5044037103652954},{"id":"https://openalex.org/keywords/access-method","display_name":"Access method","score":0.46518200635910034},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.42430227994918823},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4196474850177765},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3952488303184509},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32452237606048584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20262756943702698},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1885439157485962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601650357246399},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7561901807785034},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6859118342399597},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6811205744743347},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5790554881095886},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5651508569717407},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5345221161842346},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5044037103652954},{"id":"https://openalex.org/C70000936","wikidata":"https://www.wikidata.org/wiki/Q4672467","display_name":"Access method","level":2,"score":0.46518200635910034},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.42430227994918823},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4196474850177765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3952488303184509},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32452237606048584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20262756943702698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1885439157485962},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2015.2506556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2015.2506556","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:pure.atira.dk:publications/4b47aa88-b735-4542-a589-19d563e8f358","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85012292964&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen , L , Gao , Y , Li , X , Jensen , C S &amp; Chen , G 2017 , ' Efficient Metric Indexing for Similarity Search and Similarity Joins ' , IEEE Transactions on Knowledge and Data Engineering , vol. 29 , no. 3 , 7349200 , pp. 556-571 . https://doi.org/10.1109/TKDE.2015.2506556","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3503326317","display_name":null,"funder_award_id":"2015CB352502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4333703567","display_name":null,"funder_award_id":"61472348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7048928806","display_name":null,"funder_award_id":"61379033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8438808684","display_name":null,"funder_award_id":"61522208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2310636","https://openalex.org/W14135646","https://openalex.org/W179105903","https://openalex.org/W965825930","https://openalex.org/W980041598","https://openalex.org/W1497953515","https://openalex.org/W1523134890","https://openalex.org/W1554174647","https://openalex.org/W1564102049","https://openalex.org/W1573493856","https://openalex.org/W1603845670","https://openalex.org/W1754958282","https://openalex.org/W1963759274","https://openalex.org/W1968566320","https://openalex.org/W1971927246","https://openalex.org/W1973836650","https://openalex.org/W1994529543","https://openalex.org/W2008663777","https://openalex.org/W2009233076","https://openalex.org/W2021283827","https://openalex.org/W2037201833","https://openalex.org/W2038044292","https://openalex.org/W2046746220","https://openalex.org/W2049644877","https://openalex.org/W2065528935","https://openalex.org/W2070705506","https://openalex.org/W2071735063","https://openalex.org/W2078321579","https://openalex.org/W2091967195","https://openalex.org/W2096234514","https://openalex.org/W2096635897","https://openalex.org/W2097921974","https://openalex.org/W2104601522","https://openalex.org/W2112995410","https://openalex.org/W2115500858","https://openalex.org/W2121516976","https://openalex.org/W2122829408","https://openalex.org/W2122990007","https://openalex.org/W2133389331","https://openalex.org/W2144569695","https://openalex.org/W2157092487","https://openalex.org/W2166741129","https://openalex.org/W2167447620","https://openalex.org/W2168402437","https://openalex.org/W2197645824","https://openalex.org/W2621048125","https://openalex.org/W2769245605","https://openalex.org/W3169291629","https://openalex.org/W6600094831","https://openalex.org/W6607263069","https://openalex.org/W6632963374","https://openalex.org/W6674878074","https://openalex.org/W6678342440","https://openalex.org/W6681412881","https://openalex.org/W6682969285","https://openalex.org/W6684541063"],"related_works":["https://openalex.org/W1949910768","https://openalex.org/W1480566255","https://openalex.org/W2254397067","https://openalex.org/W1505866794","https://openalex.org/W2013685631","https://openalex.org/W2117742927","https://openalex.org/W4237360438","https://openalex.org/W1554228447","https://openalex.org/W1950643109","https://openalex.org/W2357477326"],"abstract_inverted_index":{"Spatial":[0],"queries":[1],"including":[2],"similarity":[3,6,46,153,156,194,197],"search":[4,154,195],"and":[5,19,41,59,68,85,155,172,190,196],"joins":[7,198],"are":[8,24],"useful":[9],"in":[10,49],"many":[11],"areas,":[12],"such":[13],"as":[14,158,160],"multimedia":[15],"retrieval,":[16],"data":[17,38,91,174],"integration,":[18],"so":[20],"on.":[21],"However,":[22],"they":[23],"not":[25],"supported":[26],"well":[27,159],"by":[28],"commercial":[29],"DBMSs.":[30],"This":[31,76],"may":[32],"be":[33],"due":[34],"to":[35,89,107,129],"the":[36,42,66,79,110,117,141,181],"complex":[37],"types":[39],"involved":[40],"needs":[43],"for":[44,63,151],"flexible":[45],"criteria":[47],"seen":[48],"real":[50,171],"applications.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"propose":[56],"a":[57,101,124],"versatile":[58],"efficient":[60,149,193],"disk-based":[61],"index":[62,77],"metric":[64],"data,":[65],"Space-fillingcurve":[67],"Pivot-based":[69],"B":[70,80],"<sup":[71,81],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72,82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">+</sup>":[73,83],"-tree":[74],"(SPB-tree).":[75],"leverages":[78],"-tree,":[84],"uses":[86],"space-filling":[87],"curve":[88],"cluster":[90],"into":[92,143],"compact":[93],"regions,":[94],"thus":[95],"achieving":[96],"storage":[97],"efficiency.":[98],"It":[99],"utilizes":[100],"small":[102],"set":[103],"of":[104,112,123,133],"so-called":[105],"pivots":[106],"reduce":[108],"significantly":[109],"number":[111],"distance":[113],"computations":[114],"when":[115],"using":[116,169],"index.":[118],"Further,":[119],"it":[120,137],"makes":[121],"use":[122],"separate":[125],"random":[126],"access":[127],"file":[128],"support":[130],"abroad":[131],"range":[132],"data.":[134],"By":[135],"design,":[136],"is":[138],"easyto":[139],"integrate":[140],"SPB-tree":[142,182],"an":[144],"existing":[145],"DBMS.":[146],"We":[147],"present":[148],"algorithms":[150],"processing":[152],"joins,":[157],"corresponding":[161],"cost":[162,202],"models":[163],"based":[164],"on":[165],"SPB-trees.":[166],"Extensive":[167],"experiments":[168],"both":[170],"synthetic":[173],"show":[175],"that,":[176],"compared":[177],"with":[178,199],"state-of-the-art":[179],"competitors,":[180],"has":[183],"much":[184],"lower":[185],"construction":[186],"cost,":[187],"smallerstorage":[188],"size,":[189],"supports":[191],"more":[192],"high":[200],"accuracy":[201],"models.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}