{"id":"https://openalex.org/W1989505330","doi":"https://doi.org/10.1109/bigdata.2013.6691637","title":"Terabyte-scale image similarity search: Experience and best practice","display_name":"Terabyte-scale image similarity search: Experience and best practice","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W1989505330","doi":"https://doi.org/10.1109/bigdata.2013.6691637","mag":"1989505330"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691637","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":"preprint","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/A5064457907","display_name":"Diana Moise","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Diana Moise","raw_affiliation_strings":["INRIA, Rennes, France","[INRIA Rennes, Rennes, France]"],"affiliations":[{"raw_affiliation_string":"INRIA, Rennes, France","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"[INRIA Rennes, Rennes, France]","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103329268","display_name":"Denis Shestakov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FI","FR"],"is_corresponding":false,"raw_author_name":"Denis Shestakov","raw_affiliation_strings":["INRIA, Rennes, France","INRIA Rennes, Aalto Univ., Aalto, Finland"],"affiliations":[{"raw_affiliation_string":"INRIA, Rennes, France","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA Rennes, Aalto Univ., Aalto, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003862739","display_name":"Gylfi \u00de\u00f3r Gu\u00f0mundsson","orcid":"https://orcid.org/0000-0003-0846-6617"},"institutions":[{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gylfi Gudmundsson","raw_affiliation_strings":["INRIA, Rennes, France","[INRIA Rennes, Rennes, France]"],"affiliations":[{"raw_affiliation_string":"INRIA, Rennes, France","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"[INRIA Rennes, Rennes, France]","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112422144","display_name":"Laurent Amsaleg","orcid":null},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Amsaleg","raw_affiliation_strings":["IRISA-CNR, France","IRISA, Rennes, France"],"affiliations":[{"raw_affiliation_string":"IRISA-CNR, France","institution_ids":["https://openalex.org/I2802519937"]},{"raw_affiliation_string":"IRISA, Rennes, France","institution_ids":["https://openalex.org/I2802519937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064457907"],"corresponding_institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I1326498283"],"apc_list":null,"apc_paid":null,"fwci":2.85925357,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92436331,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"20","issue":null,"first_page":"674","last_page":"682"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9952999949455261,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9947999715805054,"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/terabyte","display_name":"Terabyte","score":0.9695680737495422},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8565813302993774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8306123614311218},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5614327192306519},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5585132241249084},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5560073852539062},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5392016768455505},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5153283476829529},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2692265510559082},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16564291715621948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1392376720905304},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07246166467666626}],"concepts":[{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.9695680737495422},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8565813302993774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306123614311218},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5614327192306519},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5585132241249084},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5560073852539062},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5392016768455505},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5153283476829529},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2692265510559082},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16564291715621948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1392376720905304},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07246166467666626},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2013.6691637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691637","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W52352892","https://openalex.org/W603723648","https://openalex.org/W1984309565","https://openalex.org/W1985570011","https://openalex.org/W1999647634","https://openalex.org/W2020308406","https://openalex.org/W2040213390","https://openalex.org/W2058614910","https://openalex.org/W2058702651","https://openalex.org/W2073133286","https://openalex.org/W2096578865","https://openalex.org/W2111364199","https://openalex.org/W2119738171","https://openalex.org/W2128017662","https://openalex.org/W2132234208","https://openalex.org/W2140486418","https://openalex.org/W2150058384","https://openalex.org/W2158535916","https://openalex.org/W2173213060","https://openalex.org/W2951128501","https://openalex.org/W4231139262","https://openalex.org/W6682290801","https://openalex.org/W6991693957"],"related_works":["https://openalex.org/W2936171637","https://openalex.org/W1586214342","https://openalex.org/W2260589296","https://openalex.org/W3157828377","https://openalex.org/W181157820","https://openalex.org/W3137329302","https://openalex.org/W4241817935","https://openalex.org/W2937168573","https://openalex.org/W2805468299","https://openalex.org/W2990494149"],"abstract_inverted_index":{"While":[0],"the":[1,16,23,27,34,43,51,57,63,74,78,96,107,110,117,122,125,137,147,161],"past":[2],"decade":[3],"has":[4,48,55],"witnessed":[5],"an":[6],"unprecedented":[7],"growth":[8],"of":[9,29,33,62,77,102,106,119,124,134],"data":[10,19,108],"generated":[11],"and":[12,109,121,136,158,165],"collected":[13],"all":[14],"over":[15],"world,":[17],"existing":[18],"management":[20],"approaches":[21],"lack":[22],"ability":[24],"to":[25,115,160],"address":[26],"challenges":[28],"Big":[30,39,64,162],"Data.":[31],"One":[32],"most":[35],"promising":[36],"tools":[37,126],"for":[38,59],"Data":[40,65,163],"processing":[41,100],"is":[42],"MapReduce":[44,52,79],"paradigm.":[45,80],"Although":[46],"it":[47,127],"its":[49],"limitations,":[50],"programming":[53],"model":[54],"laid":[56],"foundations":[58],"answering":[60],"some":[61],"challenges.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,91,140],"focus":[71],"on":[72],"Hadoop,":[73],"open-source":[75],"implementation":[76],"Using":[81],"as":[82,155],"case-study":[83],"a":[84,131],"Hadoop-based":[85],"application,":[86],"i.e.,":[87],"image":[88],"similarity":[89],"search,":[90],"present":[92,130],"our":[93,144],"experiences":[94],"with":[95,146],"Hadoop":[97,120,148],"framework":[98],"when":[99],"terabytes":[101],"data.":[103],"The":[104],"scale":[105],"application":[111],"workload":[112],"allowed":[113],"us":[114],"test":[116],"limits":[118],"efficiency":[123],"provides.":[128],"We":[129],"wide":[132],"collection":[133],"experiments":[135],"practical":[138],"lessons":[139],"have":[141],"drawn":[142],"from":[143],"experience":[145],"environment.":[149],"Our":[150],"findings":[151],"can":[152],"be":[153],"shared":[154],"best":[156],"practices":[157],"recommendations":[159],"researchers":[164],"practioners.":[166]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}