{"id":"https://openalex.org/W144174343","doi":null,"title":"High-dimensional similarity search for large datasets","display_name":"High-dimensional similarity search for large datasets","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W144174343","mag":"144174343"},"language":"en","primary_location":{"id":"mag:144174343","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=2395816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5100399972","display_name":"Kai Li","orcid":"https://orcid.org/0000-0003-1560-0853","observed_orcids":["https://orcid.org/0000-0003-1560-0853"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["Princeton University#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-1560-0853","affiliations":[{"raw_affiliation_string":"Princeton University#TAB#","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086692495","display_name":"Wei Dong","orcid":"https://orcid.org/0000-0003-3067-8720","observed_orcids":["https://orcid.org/0000-0003-3067-8720"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Dong","raw_affiliation_strings":["Princeton University#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-3067-8720","affiliations":[{"raw_affiliation_string":"Princeton University#TAB#","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":0.3131,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.62939019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9580000042915344,"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":0.9580000042915344,"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":0.0071000000461936,"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/T11106","display_name":"Data Management and Algorithms","score":0.00559999980032444,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/high-dimensional-similarity-search","display_name":"high-dimensional similarity search","score":0.9810000061988831},{"id":"https://openalex.org/keywords/content-based-image-retrieval","display_name":"content-based image retrieval","score":0.9599999785423279},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"locality-sensitive hashing","score":0.8899999856948853},{"id":"https://openalex.org/keywords/performance-modeling","display_name":"performance modeling","score":0.8100000023841858},{"id":"https://openalex.org/keywords/auto-tuning","display_name":"auto-tuning","score":0.5979999899864197},{"id":"https://openalex.org/keywords/adaptive-query-processing","display_name":"adaptive query processing","score":0.699999988079071},{"id":"https://openalex.org/keywords/k-nearest-neighbors","display_name":"k-nearest neighbors","score":0.6000000238418579},{"id":"https://openalex.org/keywords/set-representation","display_name":"set representation","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.8209450244903564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7181650996208191},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6824317574501038},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5715426206588745},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5200436115264893},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47429612278938293},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42390140891075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3655768036842346},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3571091592311859},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3345981538295746},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24228301644325256},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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":1,"locations":[{"id":"mag:144174343","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=2395816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W139098497","https://openalex.org/W1491105865","https://openalex.org/W1496659369","https://openalex.org/W1502916507","https://openalex.org/W1515236863","https://openalex.org/W1541459201","https://openalex.org/W1545294102","https://openalex.org/W1561952261","https://openalex.org/W1571401318","https://openalex.org/W1627400044","https://openalex.org/W1672197616","https://openalex.org/W1835419070","https://openalex.org/W1976591483","https://openalex.org/W1981420413","https://openalex.org/W1985123706","https://openalex.org/W1991800036","https://openalex.org/W2005243064","https://openalex.org/W2011798344","https://openalex.org/W2012833704","https://openalex.org/W2029073757","https://openalex.org/W2031585418","https://openalex.org/W2045107949","https://openalex.org/W2059139185","https://openalex.org/W2062170755","https://openalex.org/W2067994867","https://openalex.org/W2071572981","https://openalex.org/W2071714241","https://openalex.org/W2080745194","https://openalex.org/W2086254934","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2100398441","https://openalex.org/W2104019579","https://openalex.org/W2107711468","https://openalex.org/W2109868644","https://openalex.org/W2111110737","https://openalex.org/W2112020727","https://openalex.org/W2112074816","https://openalex.org/W2118269922","https://openalex.org/W2119565742","https://openalex.org/W2124222502","https://openalex.org/W2128017662","https://openalex.org/W2128678576","https://openalex.org/W2129412326","https://openalex.org/W2130502756","https://openalex.org/W2130865646","https://openalex.org/W2133671054","https://openalex.org/W2134174893","https://openalex.org/W2134692386","https://openalex.org/W2141362318","https://openalex.org/W2142040641","https://openalex.org/W2143668817","https://openalex.org/W2145349611","https://openalex.org/W2145725688","https://openalex.org/W2147717514","https://openalex.org/W2148781362","https://openalex.org/W2148809531","https://openalex.org/W2150593711","https://openalex.org/W2151103935","https://openalex.org/W2151930506","https://openalex.org/W2153704625","https://openalex.org/W2154952031","https://openalex.org/W2155904486","https://openalex.org/W2159472480","https://openalex.org/W2160831612","https://openalex.org/W2161449253","https://openalex.org/W2161854574","https://openalex.org/W2162006472","https://openalex.org/W2162659160","https://openalex.org/W2162915993","https://openalex.org/W2166742463","https://openalex.org/W2171790913","https://openalex.org/W2172232203","https://openalex.org/W2293597654","https://openalex.org/W2401693723","https://openalex.org/W2435338979","https://openalex.org/W3127686677","https://openalex.org/W3148981562","https://openalex.org/W3198160809"],"related_works":["https://openalex.org/W135741203","https://openalex.org/W7099733294","https://openalex.org/W1502916507","https://openalex.org/W3196447082","https://openalex.org/W2170037597","https://openalex.org/W2531240476","https://openalex.org/W3174602507","https://openalex.org/W4250378831","https://openalex.org/W7217836331","https://openalex.org/W7098356129"],"abstract_inverted_index":{"The":[0,63],"volume":[1],"of":[2,18,60,79,94,117,152,161,193,211,249,258,309,353,362],"images":[3,35,382],"and":[4,76,97,115,179,338,388],"other":[5],"non-text":[6],"data":[7,24,46,68,315],"is":[8,25,57,65,219,318],"growing":[9],"exponentially":[10],"in":[11,214,278,335],"today's":[12],"digital":[13],"universe.":[14],"A":[15],"popular":[16,314],"way":[17],"extracting":[19],"useful":[20],"information":[21,244,277],"from":[22],"such":[23],"to":[26,32,39,44,48,100,111,169,180,187,221,238,245,274,286,294,305,390],"conduct":[27],"content-based":[28],"similarity":[29,51,119,135,251,264],"search,":[30],"e.g.,":[31],"search":[33,52,87,136,146,191,265,298,372],"for":[34,204,263],"with":[36,148,231],"content":[37],"similar":[38],"a":[40,54,158,303,368,384,393],"query":[41,184,281],"image.":[42],"How":[43],"build":[45],"structures":[47],"support":[49],"efficient":[50,201],"on":[53,383],"large":[55,92],"scale":[56],"an":[58,90,140,149,182,200,269,312,341],"issue":[59],"increasing":[61],"importance.":[62],"challenge":[64],"that":[66,82,144,285,317],"feature-rich":[67],"are":[69],"usually":[70],"represented":[71],"as":[72,83],"high-dimensional":[73,118,134,259],"feature":[74,260,310],"vectors,":[75,311,323],"the":[77,95,113,124,132,162,189,207,215,226,240,247,276,279,289,332,354,363],"curse":[78],"dimensionality":[80,84],"dictates":[81],"grows,":[85],"any":[86],"strategy":[88,186],"examines":[89],"increasingly":[91,313],"portion":[93],"dataset":[96],"eventually":[98],"degenerates":[99],"brute-force":[101],"scan.":[102],"In":[103,340],"this":[104,167],"dissertation,":[105],"we":[106,122,128,198,235,254,301,359],"study":[107],"several":[108],"key":[109],"issues":[110],"improve":[112],"accuracy":[114,147],"efficiency":[116],"search.":[120,252],"Specifically,":[121],"make":[123],"following":[125],"contributions:":[126],"\r\nFirst,":[127],"enhance":[129],"Multi-Probe":[130],"LSH,":[131],"state-of-the-art":[133,227],"technique,":[137],"by":[138,292,366],"developing":[139],"accurate":[141,320],"performance":[142,172],"model":[143,168],"predicts":[145],"error":[150],"rate":[151],"less":[153],"than":[154,225,321,378],"5%":[155],"using":[156],"only":[157],"1/10":[159],"sample":[160],"whole":[163],"dataset.":[164,216],"We":[165,267,283],"use":[166,239,284],"realize":[170],"automatic":[171],"tuning,":[173],"which":[174],"would":[175],"otherwise":[176],"be":[177],"tedious,":[178],"develop":[181,199,255,302],"adaptive":[183],"processing":[185],"ensure":[188],"high":[190],"quality":[192],"each":[194],"individual":[195],"query.":[196],"\r\nSecond,":[197],"offline":[202,241],"method":[203,218,329,346],"simultaneously":[205],"finding":[206],"K":[208],"nearest":[209],"neighbors":[210],"every":[212],"point":[213],"Our":[217,328,374],"2":[220],"16":[222],"times":[223,349],"faster":[224],"technique":[228],"when":[229],"evaluated":[230],"different":[232],"datasets.":[233],"Furthermore,":[234],"show":[236],"how":[237],"computed":[242],"nearest-neighbor":[243],"double":[246],"speed":[248],"online":[250],"\r\nThird,":[253],"compact":[256],"representations":[257],"vectors":[261],"optimized":[262],"tasks.":[266],"present":[268],"asymmetric":[270],"distance":[271],"estimation":[272],"framework":[273],"exploit":[275],"uncompressed":[280],"data.":[282],"further":[287],"compress":[288],"indexed":[290],"dataset,":[291],"10%":[293],"40%,":[295],"without":[296],"compromising":[297],"quality.":[299],"\r\nFourth,":[300],"scheme":[304],"compactly":[306],"represent":[307],"sets":[308],"representation":[316],"more":[319,326,377],"single":[322,385],"but":[324],"also":[325],"expensive.":[327],"dramatically":[330],"reduces":[331],"matching":[333],"cost":[334],"both":[336],"space":[337],"time.":[339],"image":[342,371],"classification":[343],"task,":[344],"our":[345],"achieves":[347],"25":[348],"speedup":[350],"over":[351],"one":[352],"best":[355],"existing":[356],"techniques.":[357],"\r\nFinally,":[358],"demonstrate":[360],"some":[361],"proposed":[364],"techniques":[365],"building":[367],"large-scale":[369],"near-duplicate":[370],"engine.":[373],"system":[375],"serves":[376],"50":[379],"million":[380],"web":[381],"commodity":[386],"server":[387],"responds":[389],"queries":[391],"within":[392],"few":[394],"seconds.":[395]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2016-06-24T00:00:00"}