{"id":"https://openalex.org/W1987040325","doi":"https://doi.org/10.1145/1835804.1835946","title":"Scalable similarity search with optimized kernel hashing","display_name":"Scalable similarity search with optimized kernel hashing","publication_year":2010,"publication_date":"2010-07-25","ids":{"openalex":"https://openalex.org/W1987040325","doi":"https://doi.org/10.1145/1835804.1835946","mag":"1987040325"},"language":"en","primary_location":{"id":"doi:10.1145/1835804.1835946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and 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/A5101252047","display_name":"Junfeng He","orcid":"https://orcid.org/0009-0004-5465-5659"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junfeng He","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037340457","display_name":"Shih\u2010Fu Chang","orcid":"https://orcid.org/0000-0003-1444-1205"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih-Fu Chang","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":9.518,"has_fulltext":false,"cited_by_count":152,"citation_normalized_percentile":{"value":0.98714866,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1129","last_page":"1138"},"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":1.0,"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":1.0,"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":0.9951000213623047,"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":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.7341148853302002},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.716671347618103},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5743653774261475},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.5669000744819641},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5668171644210815},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5403831601142883},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.47170281410217285},{"id":"https://openalex.org/keywords/k-independent-hashing","display_name":"K-independent hashing","score":0.4707888960838318},{"id":"https://openalex.org/keywords/feature-hashing","display_name":"Feature hashing","score":0.4652569890022278},{"id":"https://openalex.org/keywords/universal-hashing","display_name":"Universal hashing","score":0.45971348881721497},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.4581649899482727},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45663976669311523},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.45448729395866394},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.43923404812812805},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32379525899887085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1667988896369934},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14067497849464417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341148853302002},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.716671347618103},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5743653774261475},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.5669000744819641},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5668171644210815},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5403831601142883},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.47170281410217285},{"id":"https://openalex.org/C187062812","wikidata":"https://www.wikidata.org/wiki/Q6322840","display_name":"K-independent hashing","level":5,"score":0.4707888960838318},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.4652569890022278},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.45971348881721497},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.4581649899482727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45663976669311523},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.45448729395866394},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.43923404812812805},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32379525899887085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1667988896369934},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14067497849464417},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1835804.1835946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.394.990","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.394.990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.columbia.edu/ln/dvmm/publications/10/OKH_KDD2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.421.3971","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.421.3971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.columbia.edu/~wliu/KDD10_kernel_hash.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W205159212","https://openalex.org/W1502916507","https://openalex.org/W1566135517","https://openalex.org/W2019336343","https://openalex.org/W2024668293","https://openalex.org/W2049644877","https://openalex.org/W2107410045","https://openalex.org/W2111110737","https://openalex.org/W2112545207","https://openalex.org/W2125378448","https://openalex.org/W2147717514","https://openalex.org/W2151103935","https://openalex.org/W2154872931","https://openalex.org/W2154956324","https://openalex.org/W2156598602","https://openalex.org/W2156718197","https://openalex.org/W2156909104","https://openalex.org/W2162006472","https://openalex.org/W2162881463","https://openalex.org/W2162915993","https://openalex.org/W2164338181","https://openalex.org/W2166049352","https://openalex.org/W2171790913","https://openalex.org/W2293597654","https://openalex.org/W2913932916","https://openalex.org/W3144386677","https://openalex.org/W4234552385","https://openalex.org/W4256017923","https://openalex.org/W6676388157","https://openalex.org/W6676930901","https://openalex.org/W6682644385","https://openalex.org/W6683954003","https://openalex.org/W6684181414","https://openalex.org/W6697214482","https://openalex.org/W6758860047"],"related_works":["https://openalex.org/W2100189723","https://openalex.org/W1554555624","https://openalex.org/W1998749283","https://openalex.org/W1997107867","https://openalex.org/W2253231004","https://openalex.org/W4212830455","https://openalex.org/W2104208555","https://openalex.org/W1982193706","https://openalex.org/W2074668987","https://openalex.org/W4292730591"],"abstract_inverted_index":{"Scalable":[0],"similarity":[1],"search":[2],"is":[3,24,170],"the":[4,40,97,171,218,227],"core":[5],"of":[6,78,133,167,177],"many":[7,16],"large":[8,75,207],"scale":[9,76,208],"learning":[10],"or":[11],"data":[12,33,77,162,203],"mining":[13],"applications.":[14],"Recently,":[15],"research":[17],"results":[18,216],"demonstrate":[19],"that":[20,31,110],"one":[21],"promising":[22],"approach":[23],"creating":[25],"compact":[26,127],"and":[27,92,105,120,122,149,154,188,201],"efficient":[28,72,139],"hash":[29,53,114,128],"codes":[30,73,129],"preserve":[32],"similarity.":[34],"By":[35],"efficient,":[36],"we":[37,64,137],"refer":[38],"to":[39,70,100,125,145,160,173,180,210],"low":[41,45],"correlation":[42],"(and":[43],"thus":[44],"redundancy)":[46],"among":[47],"generated":[48],"codes.":[49],"However,":[50],"most":[51,234],"existing":[52],"methods":[54],"are":[55,107],"designed":[56],"only":[57],"for":[58,74,130,152,225,233],"vector":[59,200],"data.":[60],"In":[61],"this":[62],"paper,":[63],"develop":[65],"a":[66,111,206,230],"new":[67,131],"hashing":[68],"algorithm":[69,158],"create":[71],"general":[79,134],"formats":[80],"with":[81,96,229],"any":[82],"kernel":[83,112],"function,":[84],"including":[85,184],"kernels":[86],"on":[87],"vectors,":[88],"graphs,":[89],"sequences,":[90],"sets":[91,204],"so":[93],"on.":[94],"Starting":[95],"idea":[98],"analogous":[99],"spectral":[101],"hashing,":[102],"novel":[103],"formulations":[104],"solutions":[106],"proposed":[108,219],"such":[109,141],"based":[113],"function":[115],"can":[116],"be":[117],"explicitly":[118],"represented":[119],"optimized,":[121],"directly":[123],"applied":[124],"compute":[126],"samples":[132],"formats.":[135],"Moreover,":[136],"incorporate":[138],"techniques,":[140],"as":[142],"Nystrom":[143],"approximation,":[144],"further":[146],"reduce":[147],"time":[148],"space":[150],"complexity":[151],"indexing":[153],"search,":[155],"making":[156],"our":[157,168,196],"scalable":[159],"huge":[161],"sets.":[163],"Another":[164],"important":[165],"advantage":[166],"method":[169,197,220],"ability":[172],"handle":[174],"diverse":[175],"types":[176],"similarities":[178,187,190],"according":[179],"actual":[181],"task":[182],"requirements,":[183],"both":[185,199],"feature":[186],"semantic":[189],"like":[191],"label":[192],"consistency.":[193],"We":[194],"evaluate":[195],"using":[198],"non-vector":[202],"at":[205],"up":[209],"1":[211],"million":[212],"samples.":[213],"Our":[214],"comprehensive":[215],"show":[217],"outperforms":[221],"several":[222],"state-of-the-art":[223],"approaches":[224],"all":[226],"tasks,":[228],"significant":[231],"gain":[232],"tasks.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":21}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}