{"id":"https://openalex.org/W1974775589","doi":"https://doi.org/10.1145/1631058.1631067","title":"Large-scale multimedia semantic concept modeling using robust subspace bagging and MapReduce","display_name":"Large-scale multimedia semantic concept modeling using robust subspace bagging and MapReduce","publication_year":2009,"publication_date":"2009-10-23","ids":{"openalex":"https://openalex.org/W1974775589","doi":"https://doi.org/10.1145/1631058.1631067","mag":"1974775589"},"language":"en","primary_location":{"id":"doi:10.1145/1631058.1631067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631058.1631067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining","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/A5033563552","display_name":"Rong Yan","orcid":"https://orcid.org/0000-0001-7925-1280"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rong Yan","raw_affiliation_strings":["IBM Research, Hawthorne, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002379018","display_name":"Marc-Olivier Fleury","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marc-Olivier Fleury","raw_affiliation_strings":["EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068061267","display_name":"Michele Merler","orcid":"https://orcid.org/0000-0002-4358-8671"},"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":"Michele Merler","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/A5030886753","display_name":"Apostol Natsev","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apostol Natsev","raw_affiliation_strings":["IBM Research, Hawthorne, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105523625","display_name":"John R. Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Smith","raw_affiliation_strings":["IBM Research, Hawthorne, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5697,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96912737,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"42"},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9976000189781189,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9857000112533569,"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":0.9019871950149536},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8100924491882324},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7815223336219788},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6959452033042908},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5696455240249634},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5381209850311279},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5290184020996094},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5133628249168396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.503400981426239},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.49342551827430725},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48600825667381287},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4166921079158783},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3752366304397583},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2747778296470642},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14986750483512878},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09140324592590332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9019871950149536},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8100924491882324},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7815223336219788},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6959452033042908},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5696455240249634},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5381209850311279},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5290184020996094},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5133628249168396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503400981426239},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.49342551827430725},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48600825667381287},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4166921079158783},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3752366304397583},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2747778296470642},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14986750483512878},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09140324592590332},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1631058.1631067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631058.1631067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1574862351","https://openalex.org/W1578100948","https://openalex.org/W1861377444","https://openalex.org/W1980264541","https://openalex.org/W1986482242","https://openalex.org/W1995276998","https://openalex.org/W2019133545","https://openalex.org/W2025363509","https://openalex.org/W2084802027","https://openalex.org/W2099262739","https://openalex.org/W2109722477","https://openalex.org/W2113242816","https://openalex.org/W2122389422","https://openalex.org/W2138516811","https://openalex.org/W2173213060","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W2990138404","https://openalex.org/W3021461773","https://openalex.org/W3041351009","https://openalex.org/W4210351656","https://openalex.org/W6628754449","https://openalex.org/W6634462686","https://openalex.org/W6676367512"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2393964553","https://openalex.org/W2913534066","https://openalex.org/W3138386522","https://openalex.org/W2970375204","https://openalex.org/W2499279132","https://openalex.org/W2067869703"],"abstract_inverted_index":{"With":[0],"the":[1,32,61,133,142,152,156],"rapid":[2],"growth":[3],"of":[4,63,102,158],"multimedia":[5],"data,":[6],"it":[7],"becomes":[8],"increasingly":[9],"important":[10],"to":[11,91],"develop":[12,86],"semantic":[13],"concept":[14],"modeling":[15,50],"approaches":[16],"that":[17],"are":[18],"consistently":[19],"effective,":[20],"highly":[21],"efficient,":[22],"and":[23,107],"easily":[24],"scalable.":[25],"To":[26,80],"this":[27],"end,":[28],"we":[29,84],"first":[30],"propose":[31],"robust":[33],"subspace":[34,41],"bagging":[35,42],"(RB-SBag)":[36],"algorithm":[37,90],"by":[38],"augmenting":[39],"random":[40],"with":[43,48,120],"forward":[44],"model":[45],"selection.":[46],"Compared":[47],"traditional":[49],"approaches,":[51],"RB-SBag":[52,113],"offers":[53],"a":[54,70,74,87,99,117,137,147],"considerably":[55],"faster":[56],"learning":[57],"process":[58],"while":[59],"minimizing":[60],"risk":[62],"overfitting.":[64],"Its":[65],"ensemble":[66],"structure":[67],"also":[68,85,131],"enables":[69],"convenient":[71],"transformation":[72],"into":[73],"simple":[75],"parallel":[76],"framework":[77],"called":[78],"MapReduce.":[79],"further":[81],"improve":[82],"scalability,":[83],"task":[88,93,144,159],"scheduling":[89],"optimize":[92],"placement":[94],"for":[95],"heterogenous":[96],"tasks.":[97],"On":[98],"collection":[100],"consisting":[101],"more":[103,115],"than":[104,116,127,151],"250,000":[105],"images":[106],"several":[108],"standard":[109],"TRECVID":[110],"benchmark":[111],"datasets,":[112],"achieved":[114],"10-fold":[118],"speedup":[119],"comparable":[121],"or":[122],"even":[123],"better":[124,149],"classification":[125],"performance":[126],"baseline":[128,153],"SVMs.":[129],"We":[130],"deployed":[132],"MapReduce":[134],"implementation":[135],"on":[136],"16-node":[138],"Hadoop":[139],"cluster,":[140],"where":[141],"proposed":[143],"scheduler":[145,154],"demonstrates":[146],"significantly":[148],"scalability":[150],"in":[155],"presence":[157],"heterogeneity.":[160]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}