{"id":"https://openalex.org/W1835419070","doi":"https://doi.org/10.1145/1835449.1835455","title":"Self-taught hashing for fast similarity search","display_name":"Self-taught hashing for fast similarity search","publication_year":2010,"publication_date":"2010-07-19","ids":{"openalex":"https://openalex.org/W1835419070","doi":"https://doi.org/10.1145/1835449.1835455","mag":"1835419070"},"language":"en","primary_location":{"id":"doi:10.1145/1835449.1835455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","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/A5015784640","display_name":"Dell Zhang","orcid":"https://orcid.org/0000-0002-8774-3725"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["Birkbeck, University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Birkbeck, University of London, London, United Kingdom","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384767","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-5890-0365"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"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":"Deng Cai","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang university, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang university, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104256708","display_name":"Jinsong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinsong Lu","raw_affiliation_strings":["Birkbeck, University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Birkbeck, University of London, London, United Kingdom","institution_ids":["https://openalex.org/I98259816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015784640"],"corresponding_institution_ids":["https://openalex.org/I98259816"],"apc_list":null,"apc_paid":null,"fwci":17.7787,"has_fulltext":false,"cited_by_count":356,"citation_normalized_percentile":{"value":0.99472252,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"25"},"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":0.9998000264167786,"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":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9879999756813049,"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":0.7149460911750793},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.592943549156189},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5568142533302307},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.46141374111175537},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.4207625389099121},{"id":"https://openalex.org/keywords/self-similarity","display_name":"Self-similarity","score":0.41926825046539307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3621944785118103},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.34752023220062256},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3361009955406189},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3293251395225525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12984707951545715},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1092275083065033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149460911750793},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.592943549156189},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5568142533302307},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.46141374111175537},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.4207625389099121},{"id":"https://openalex.org/C119453123","wikidata":"https://www.wikidata.org/wiki/Q262372","display_name":"Self-similarity","level":2,"score":0.41926825046539307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3621944785118103},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.34752023220062256},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3361009955406189},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3293251395225525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12984707951545715},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1092275083065033},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1835449.1835455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320184","display_name":"London Mathematical Society","ror":"https://ror.org/01r1e1h27"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1532325895","https://openalex.org/W1540550673","https://openalex.org/W1541459201","https://openalex.org/W1562412850","https://openalex.org/W1578099820","https://openalex.org/W1604792744","https://openalex.org/W1974942389","https://openalex.org/W1994389483","https://openalex.org/W1995875735","https://openalex.org/W2005422315","https://openalex.org/W2019076926","https://openalex.org/W2035720976","https://openalex.org/W2053017876","https://openalex.org/W2062028408","https://openalex.org/W2070996757","https://openalex.org/W2072773380","https://openalex.org/W2085922539","https://openalex.org/W2097308346","https://openalex.org/W2100495367","https://openalex.org/W2103018059","https://openalex.org/W2109749916","https://openalex.org/W2112490010","https://openalex.org/W2118020653","https://openalex.org/W2118585731","https://openalex.org/W2121947440","https://openalex.org/W2122922389","https://openalex.org/W2125531986","https://openalex.org/W2136922672","https://openalex.org/W2139140682","https://openalex.org/W2145065594","https://openalex.org/W2147069236","https://openalex.org/W2147152072","https://openalex.org/W2149684865","https://openalex.org/W2152926413","https://openalex.org/W2154872931","https://openalex.org/W2154956324","https://openalex.org/W2160840682","https://openalex.org/W2165966284","https://openalex.org/W2166563371","https://openalex.org/W2168020168","https://openalex.org/W2168467811","https://openalex.org/W2170654002","https://openalex.org/W2171011251","https://openalex.org/W2293597654","https://openalex.org/W2560674852","https://openalex.org/W2613433911","https://openalex.org/W2616052791","https://openalex.org/W2752061190","https://openalex.org/W2752853835","https://openalex.org/W2752885492","https://openalex.org/W2798909945","https://openalex.org/W2913932916","https://openalex.org/W3001645704","https://openalex.org/W3023786531","https://openalex.org/W3145128584","https://openalex.org/W4240726888","https://openalex.org/W4285719527","https://openalex.org/W6614676750","https://openalex.org/W6633616865","https://openalex.org/W6634702315","https://openalex.org/W6677103492","https://openalex.org/W6681698864","https://openalex.org/W6682644385","https://openalex.org/W6697214482","https://openalex.org/W6744529318","https://openalex.org/W6750968397","https://openalex.org/W7029321148"],"related_works":["https://openalex.org/W3094967175","https://openalex.org/W2135779989","https://openalex.org/W2045263322","https://openalex.org/W2166822184","https://openalex.org/W2145863369","https://openalex.org/W2393322642","https://openalex.org/W3096071782","https://openalex.org/W50423144","https://openalex.org/W2144265691","https://openalex.org/W2754607325"],"abstract_inverted_index":{"The":[0],"ability":[1],"of":[2,10,38],"fast":[3],"similarity":[4,24],"search":[5,25],"at":[6],"large":[7,36],"scale":[8],"is":[9,26],"great":[11],"importance":[12],"to":[13,22,47,62,79,100,129],"many":[14],"Information":[15],"Retrieval":[16],"(IR)":[17],"applications.":[18],"A":[19],"promising":[20],"way":[21],"accelerate":[23],"semantic":[27,101],"hashing":[28],"which":[29],"designs":[30],"compact":[31],"binary":[32,109],"codes":[33,49,65,73,110],"for":[34,66,74,111,134],"a":[35,51,81,94],"number":[37],"documents":[39,44,67,77,113],"so":[40],"that":[41,148],"semantically":[42],"similar":[43,48],"are":[45,60],"mapped":[46],"(within":[50],"short":[52],"Hamming":[53],"distance).":[54],"Although":[55],"some":[56],"recently":[57],"proposed":[58,150],"techniques":[59,165],"able":[61],"generate":[63],"high-quality":[64],"known":[68],"in":[69,114],"advance,":[70],"obtaining":[71],"the":[72,106,115,131,149],"previously":[75],"unseen":[76,138],"remains":[78],"be":[80],"very":[82],"challenging":[83],"problem.":[84],"In":[85],"this":[86,90],"paper,":[87],"we":[88,103],"emphasise":[89],"issue":[91],"and":[92,121,157],"propose":[93],"novel":[95],"Self-Taught":[96],"Hashing":[97],"(STH)":[98],"approach":[99,151],"hashing:":[102],"first":[104],"find":[105],"optimal":[107],"l-bit":[108,132],"all":[112],"given":[116],"corpus":[117],"via":[118,126],"unsupervised":[119],"learning,":[120],"then":[122],"train":[123],"l":[124],"classifiers":[125],"supervised":[127],"learning":[128],"predict":[130],"code":[133],"any":[135],"query":[136],"document":[137],"before.":[139],"Our":[140],"experiments":[141],"on":[142],"three":[143],"real-world":[144],"text":[145],"datasets":[146],"show":[147],"using":[152],"binarised":[153],"Laplacian":[154],"Eigenmap":[155],"(LapEig)":[156],"linear":[158],"Support":[159],"Vector":[160],"Machine":[161],"(SVM)":[162],"outperforms":[163],"state-of-the-art":[164],"significantly.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":39},{"year":2015,"cited_by_count":48},{"year":2014,"cited_by_count":50},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":21}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}