{"id":"https://openalex.org/W2062493685","doi":"https://doi.org/10.1109/bigdata.2013.6691730","title":"Nearest neighbor classification using bottom-k sketches","display_name":"Nearest neighbor classification using bottom-k sketches","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2062493685","doi":"https://doi.org/10.1109/bigdata.2013.6691730","mag":"2062493685"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","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/A5043525193","display_name":"S\u00f8ren Dahlgaard","orcid":"https://orcid.org/0000-0003-2925-746X"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Soren Dahlgaard","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen","Department of Computer Science, Department of Computer Science, Faculty of Science, K\u00f8benhavns Universitet"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"Department of Computer Science, Department of Computer Science, Faculty of Science, K\u00f8benhavns Universitet","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042628612","display_name":"Christian Igel","orcid":"https://orcid.org/0000-0003-2868-0856"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Christian Igel","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen","Department of Computer Science, Department of Computer Science, Faculty of Science, K\u00f8benhavns Universitet"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"Department of Computer Science, Department of Computer Science, Faculty of Science, K\u00f8benhavns Universitet","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039232562","display_name":"Mikkel Thorup","orcid":"https://orcid.org/0000-0001-5237-1709"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mikkel Thorup","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen","Department of Computer Science, Faculty of Science, K\u00f8benhavns Universitet"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"Department of Computer Science, Faculty of Science, K\u00f8benhavns Universitet","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043525193"],"corresponding_institution_ids":["https://openalex.org/I124055696"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.12754961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"28","last_page":"34"},"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":0.9988999962806702,"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/T10057","display_name":"Face and Expression Recognition","score":0.9976000189781189,"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/hash-function","display_name":"Hash function","score":0.7540963888168335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6926419734954834},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6365371346473694},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5657980442047119},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5643779635429382},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5569879412651062},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5331320762634277},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5223904252052307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49413636326789856},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.47653207182884216},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3795618712902069},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35710608959198},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.2821204662322998}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7540963888168335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6926419734954834},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6365371346473694},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5657980442047119},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5643779635429382},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5569879412651062},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5331320762634277},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5223904252052307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49413636326789856},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.47653207182884216},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3795618712902069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35710608959198},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2821204662322998},{"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":3,"locations":[{"id":"doi:10.1109/bigdata.2013.6691730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.712.5609","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.712.5609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://image.diku.dk/igel/paper/NNCUBkS.pdf","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/d34f1d34-6baa-4d11-bf0b-45555e3df245","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/d34f1d34-6baa-4d11-bf0b-45555e3df245","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dahlgaard , S , Igel , C & Thorup , M 2013 , Nearest neighbor classification using bottom-k sketches . in 2013 IEEE International Conference on Big Data : proceedings . IEEE , pp. 28-34 , IEEE International Conference on Big Data 2013 , Santa Clara, CA , United States , 28/06/2013 . https://doi.org/10.1109/BigData.2013.6691730","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1546441687","https://openalex.org/W1851100088","https://openalex.org/W1979795732","https://openalex.org/W1979819093","https://openalex.org/W2070996757","https://openalex.org/W2097865464","https://openalex.org/W2102221597","https://openalex.org/W2107275319","https://openalex.org/W2112490010","https://openalex.org/W2118585731","https://openalex.org/W2119821739","https://openalex.org/W2132069633","https://openalex.org/W2134212491","https://openalex.org/W2140431670","https://openalex.org/W2152565070","https://openalex.org/W2153635508","https://openalex.org/W2245536463","https://openalex.org/W4239510810","https://openalex.org/W6645430912","https://openalex.org/W6674970736","https://openalex.org/W6675920320","https://openalex.org/W6677103492","https://openalex.org/W6677656871","https://openalex.org/W6679663036"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W2368606575","https://openalex.org/W2144265691","https://openalex.org/W4246757943","https://openalex.org/W3094967175","https://openalex.org/W2166822184","https://openalex.org/W2902799860","https://openalex.org/W4289129280","https://openalex.org/W2889587792"],"abstract_inverted_index":{"Bottom-k":[0],"sketches":[1,7,75,146],"are":[2,30,84],"an":[3],"alternative":[4],"to":[5,11,32,86,96,150],"k\u00d7minwise":[6,43,112,157],"when":[8,69],"using":[9,151],"hashing":[10,113,158],"estimate":[12],"the":[13,40,45,57,81,160,168],"similarity":[14,22],"of":[15,42,56,60,93,104,110,162,170],"documents":[16,98],"represented":[17],"by":[18,48,100],"shingles":[19,105],"(or":[20],"set":[21],"in":[23,25],"general)":[24],"large-scale":[26],"machine":[27,122],"learning.":[28],"They":[29],"faster":[31],"compute":[33],"and":[34,155],"have":[35],"nicer":[36],"theoretical":[37],"properties.":[38],"In":[39,72],"case":[41],"hashing,":[44],"bias":[46,64],"introduced":[47],"not":[49],"truly":[50],"random":[51],"hash":[52],"function":[53],"is":[54,114,165,172],"independent":[55],"number":[58,103,169],"k":[59,68],"hashes,":[61],"while":[62],"this":[63],"decreases":[65],"with":[66,90,144],"increasing":[67],"employing":[70],"bottom-k.":[71],"practice,":[73],"bottom-k":[74,145],"can":[76,117,147],"expedite":[77],"classification":[78],"systems":[79],"if":[80,159],"trained":[82],"classifiers":[83],"applied":[85],"many":[87,97],"data":[88,164],"points":[89],"a":[91,101,140,152],"lot":[92],"features":[94,171],"(i.e.,":[95],"encoded":[99],"large":[102],"on":[106,126],"average).":[107],"An":[108],"advantage":[109],"b-bit":[111,156],"that":[115,139],"it":[116],"be":[118,148],"efficiently":[119],"incorporated":[120],"into":[121],"learning":[123],"methods":[124],"relying":[125],"scalar":[127],"products,":[128],"such":[129],"as":[130],"support":[131],"vector":[132],"machines":[133],"(SVMs).":[134],"Still,":[135],"experimental":[136],"results":[137],"indicate":[138],"nearest":[141],"neighbors":[142],"classifier":[143],"preferable":[149],"linear":[153],"SVM":[154],"amount":[161],"training":[163],"low":[166],"or":[167],"high.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}