{"id":"https://openalex.org/W3007575975","doi":"https://doi.org/10.1109/bigdata47090.2019.9006324","title":"b-Bit Sketch Trie: Scalable Similarity Search on Integer Sketches","display_name":"b-Bit Sketch Trie: Scalable Similarity Search on Integer Sketches","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007575975","doi":"https://doi.org/10.1109/bigdata47090.2019.9006324","mag":"3007575975"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (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/A5021315429","display_name":"S Kanda","orcid":"https://orcid.org/0000-0002-5462-122X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shunsuke Kanda","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021642801","display_name":"Yasuo Tabei","orcid":"https://orcid.org/0000-0003-2368-5607"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Tabei","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021315429"],"corresponding_institution_ids":["https://openalex.org/I4210126580"],"apc_list":null,"apc_paid":null,"fwci":0.3037,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6259025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"99","issue":null,"first_page":"810","last_page":"819"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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":0.9991999864578247,"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/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.7807870507240295},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7080245018005371},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6842905879020691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6229863166809082},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.594710111618042},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.5393718481063843},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5348011255264282},{"id":"https://openalex.org/keywords/hamming-space","display_name":"Hamming space","score":0.48146072030067444},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4619671702384949},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.45653021335601807},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4512844681739807},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.450417697429657},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4040026366710663},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3257075846195221},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3247385621070862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26814770698547363},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.20484864711761475},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19362980127334595},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.17138099670410156},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1404833197593689}],"concepts":[{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.7807870507240295},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7080245018005371},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6842905879020691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6229863166809082},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.594710111618042},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.5393718481063843},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5348011255264282},{"id":"https://openalex.org/C2779494224","wikidata":"https://www.wikidata.org/wiki/Q5645799","display_name":"Hamming space","level":5,"score":0.48146072030067444},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4619671702384949},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.45653021335601807},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4512844681739807},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.450417697429657},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4040026366710663},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3257075846195221},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3247385621070862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26814770698547363},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.20484864711761475},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19362980127334595},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.17138099670410156},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1404833197593689},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","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},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W185552495","https://openalex.org/W1502916507","https://openalex.org/W1545097943","https://openalex.org/W1554285337","https://openalex.org/W1729998890","https://openalex.org/W1962019683","https://openalex.org/W1999092742","https://openalex.org/W2016273390","https://openalex.org/W2019450130","https://openalex.org/W2041878876","https://openalex.org/W2049993534","https://openalex.org/W2061873838","https://openalex.org/W2078677252","https://openalex.org/W2085218027","https://openalex.org/W2085922539","https://openalex.org/W2109803107","https://openalex.org/W2114043710","https://openalex.org/W2122196799","https://openalex.org/W2132234208","https://openalex.org/W2140431670","https://openalex.org/W2145349611","https://openalex.org/W2145607950","https://openalex.org/W2149243190","https://openalex.org/W2152565070","https://openalex.org/W2154956324","https://openalex.org/W2158495986","https://openalex.org/W2167847032","https://openalex.org/W2169350523","https://openalex.org/W2176433769","https://openalex.org/W2337480916","https://openalex.org/W2340526756","https://openalex.org/W2529376784","https://openalex.org/W2795250672","https://openalex.org/W2795518213","https://openalex.org/W2798891709","https://openalex.org/W2963517218","https://openalex.org/W2982188423","https://openalex.org/W3102192406","https://openalex.org/W6629956336","https://openalex.org/W6633161151","https://openalex.org/W6641201905","https://openalex.org/W6676900726"],"related_works":["https://openalex.org/W2036753599","https://openalex.org/W1993530675","https://openalex.org/W4212842756","https://openalex.org/W2772529866","https://openalex.org/W3109217364","https://openalex.org/W3026621621","https://openalex.org/W2949049896","https://openalex.org/W2089632823","https://openalex.org/W2977099505","https://openalex.org/W3007575975"],"abstract_inverted_index":{"Recently,":[0],"randomly":[1],"mapping":[2,23],"vectorial":[3],"data":[4,89,93,98],"to":[5],"strings":[6],"of":[7,47,108,143,155,172,186,199],"discrete":[8],"symbols":[9],"(i.e.,":[10,91],"sketches)":[11],"for":[12,51,79],"fast":[13],"and":[14,28,104,131,153],"space-efficient":[15,70,92],"similarity":[16,31,41,81,134,157,165,177,194],"searches":[17,42,55,82,135,195],"has":[18],"become":[19],"popular.":[20],"Such":[21],"random":[22],"is":[24,126,167],"called":[25],"similarity-preserving":[26],"hashing":[27],"approximates":[29],"a":[30,68,105,123,189],"metric":[32],"by":[33,83,139],"using":[34,118],"the":[35,85,101,137,144,150,156],"Hamming":[36],"distance.":[37],"Although":[38],"many":[39],"efficient":[40],"have":[43],"been":[44],"proposed,":[45],"most":[46,169],"them":[48],"are":[49,59],"designed":[50],"binary":[52],"sketches.":[53],"Similarity":[54],"on":[56,76,136,188],"integer":[57,77,109,129],"sketches":[58,78,110,130],"in":[60,100],"their":[61],"infancy.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"present":[67],"novel":[69],"trie":[71,75],"named":[72],"b-bit":[73],"sketch":[74],"scalable":[80],"leveraging":[84],"idea":[86],"behind":[87],"succinct":[88],"structures":[90,94],"while":[95,192],"supporting":[96],"various":[97],"operations":[99],"compressed":[102],"format)":[103],"favorable":[106],"property":[107],"as":[111],"fixed-length":[112],"strings.":[113],"Our":[114],"experimental":[115,160],"results":[116,161],"obtained":[117],"real-world":[119],"datasets":[120],"show":[121,162],"that":[122,163],"trie-based":[124],"index":[125,138],"built":[127],"from":[128],"efficiently":[132],"performs":[133],"pruning":[140],"useless":[141],"portions":[142],"search":[145,151,166],"space,":[146],"which":[147],"greatly":[148],"improves":[149],"time":[152],"space-efficiency":[154],"search.":[158],"The":[159],"our":[164,180],"at":[168],"one":[170],"order":[171],"magnitude":[173],"faster":[174],"than":[175],"state-of-the-art":[176,193],"searches.":[178],"Besides,":[179],"method":[181],"needs":[182],"only":[183],"10":[184],"GiB":[185,198],"memory":[187],"billion-scale":[190],"database,":[191],"need":[196],"29":[197],"memory.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}