{"id":"https://openalex.org/W2067393637","doi":"https://doi.org/10.1109/icdm.2013.119","title":"Min-Max Hash for Jaccard Similarity","display_name":"Min-Max Hash for Jaccard Similarity","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2067393637","doi":"https://doi.org/10.1109/icdm.2013.119","mag":"2067393637"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2013.119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2013.119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 13th International Conference on Data Mining","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/A5057952725","display_name":"Jianqiu Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiu Ji","raw_affiliation_strings":["Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372739","display_name":"Jianmin Li","orcid":"https://orcid.org/0000-0002-4937-2433"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Li","raw_affiliation_strings":["Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore","[Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"[Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore]","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111172356","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Dept. of Comput. Sci., Univ. of Texas at San Antonio, San Antonio, TX, USA",": Department of Computer Science, University of Texas at San Antonio, San Antonio, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Texas at San Antonio, San Antonio, TX, USA","institution_ids":["https://openalex.org/I45438204"]},{"raw_affiliation_string":": Department of Computer Science, University of Texas at San Antonio, San Antonio, TX, USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100335187","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0002-9958-6181"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.75734988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"309"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9850000143051147,"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/jaccard-index","display_name":"Jaccard index","score":0.8946101665496826},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.8138260841369629},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.7791625261306763},{"id":"https://openalex.org/keywords/rolling-hash","display_name":"Rolling hash","score":0.6376482248306274},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.5983089804649353},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.5828836560249329},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49996137619018555},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.460803747177124},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.443793922662735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4133446514606476},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4040154814720154},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21319234371185303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.12553703784942627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0722130537033081}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8946101665496826},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.8138260841369629},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.7791625261306763},{"id":"https://openalex.org/C108546238","wikidata":"https://www.wikidata.org/wiki/Q4228982","display_name":"Rolling hash","level":5,"score":0.6376482248306274},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.5983089804649353},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.5828836560249329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49996137619018555},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.460803747177124},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.443793922662735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4133446514606476},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4040154814720154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21319234371185303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.12553703784942627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0722130537033081},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdm.2013.119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2013.119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 13th International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/83960","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/83960","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1579524835","https://openalex.org/W1998840390","https://openalex.org/W2012833704","https://openalex.org/W2055906546","https://openalex.org/W2060536778","https://openalex.org/W2086694417","https://openalex.org/W2111295912","https://openalex.org/W2112036337","https://openalex.org/W2130484710","https://openalex.org/W2132069633","https://openalex.org/W2140129471","https://openalex.org/W2140431670","https://openalex.org/W2147017814","https://openalex.org/W2147717514","https://openalex.org/W2162006472","https://openalex.org/W2171448996","https://openalex.org/W2172232203","https://openalex.org/W2397770138","https://openalex.org/W4230940751","https://openalex.org/W6634582620","https://openalex.org/W6676877524","https://openalex.org/W6679385738","https://openalex.org/W6682042839"],"related_works":["https://openalex.org/W1985245705","https://openalex.org/W2169139294","https://openalex.org/W1996864362","https://openalex.org/W1600184780","https://openalex.org/W3131985603","https://openalex.org/W2333289748","https://openalex.org/W4318193138","https://openalex.org/W865623885","https://openalex.org/W1719676592","https://openalex.org/W2783286101"],"abstract_inverted_index":{"Min-wise":[0],"hash":[1,26,47,77,96,108,135,138],"is":[2,20,86,97],"a":[3,60],"widely-used":[4],"hashing":[5,53,141],"method":[6],"for":[7,28,89],"scalable":[8],"similarity":[9],"search":[10],"in":[11,17,65,159,171],"terms":[12],"of":[13,75,134,149],"Jaccard":[14,69,163],"similarity,":[15,164],"while":[16,152],"practice":[18],"it":[19,58,85,122],"necessary":[21],"to":[22,32,113,120,143],"compute":[23],"many":[24,103],"such":[25],"functions":[27],"certain":[29],"precision,":[30],"leading":[31],"expensive":[33],"computational":[34],"cost.":[35],"In":[36,71],"this":[37],"paper,":[38],"we":[39,117],"introduce":[40],"an":[41],"effective":[42],"method,":[43,48],"i.e.":[44],"the":[45,52,73,131,140],"min-max":[46,76,95,114,137],"which":[49],"significantly":[50],"reduces":[51,139],"time":[54,142],"by":[55],"half,":[56],"yet":[57],"has":[59],"provably":[61],"slightly":[62],"smaller":[63,154],"variance":[64],"estimating":[66,160],"pair":[67,80,161],"wise":[68,81,162],"similarity.":[70],"addition,":[72],"estimator":[74],"only":[78],"contains":[79],"equality":[82],"checking,":[83],"thus":[84],"especially":[87],"suitable":[88],"approximate":[90,168,172],"nearest":[91,173],"neighbor":[92,174],"search.":[93,175],"Since":[94],"equally":[98],"simple":[99],"as":[100,145,147],"min-wise":[101,107,150],"hash,":[102,115,151],"extensions":[104],"based":[105],"on":[106],"can":[109],"be":[110],"easily":[111],"adapted":[112],"and":[116,165],"show":[118,128],"how":[119],"combine":[121],"with":[123,130],"b-bit":[124],"minwise":[125],"hash.":[126],"Experiments":[127],"that":[129,148],"same":[132],"length":[133],"code,":[136],"half":[144],"much":[146],"achieving":[153],"mean":[155],"squared":[156],"error":[157],"(MSE)":[158],"better":[166],"best":[167],"ratio":[169],"(BAR)":[170]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}