{"id":"https://openalex.org/W2097735973","doi":null,"title":"Joint Cascade Optimization Using A Product Of Boosted Classifiers","display_name":"Joint Cascade Optimization Using A Product Of Boosted Classifiers","publication_year":2010,"publication_date":"2010-12-06","ids":{"openalex":"https://openalex.org/W2097735973","mag":"2097735973"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.8008","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.8008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cvlab.epfl.ch/%7Efleuret/papers/lefakis-fleuret-nips2010.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/164044","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077836087","display_name":"Leonidas Lefakis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Leonidas Lefakis","raw_affiliation_strings":["IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076094010","display_name":"Fran\u00e7ois Fleuret","orcid":"https://orcid.org/0000-0001-9457-7393","observed_orcids":["https://orcid.org/0000-0001-9457-7393"]},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Fleuret","raw_affiliation_strings":["IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-9457-7393","affiliations":[{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":2.6447,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90016499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":"23","issue":null,"first_page":"1315","last_page":"1323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8794000148773193,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8794000148773193,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.04919999837875366,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.02449999935925007,"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/object-detection","display_name":"object detection","score":0.7870000004768372},{"id":"https://openalex.org/keywords/cascade-classifier","display_name":"cascade classifier","score":0.7620000243186951},{"id":"https://openalex.org/keywords/boosted-classifiers","display_name":"boosted classifiers","score":0.6330000162124634},{"id":"https://openalex.org/keywords/probability-estimation","display_name":"probability estimation","score":0.3869999945163727},{"id":"https://openalex.org/keywords/face-detection","display_name":"face detection","score":0.9139999747276306},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"pedestrian detection","score":1.0}],"concepts":[{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.8336088061332703},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8184443712234497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278373837471008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.66959148645401},{"id":"https://openalex.org/C40651066","wikidata":"https://www.wikidata.org/wiki/Q5048220","display_name":"Cascading classifiers","level":4,"score":0.624100923538208},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6064231395721436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5709935426712036},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.5620335340499878},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.545881986618042},{"id":"https://openalex.org/C106135958","wikidata":"https://www.wikidata.org/wiki/Q7291993","display_name":"Random subspace method","level":3,"score":0.5224812626838684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4994392395019531},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.09099406003952026},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.8008","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.8008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cvlab.epfl.ch/%7Efleuret/papers/lefakis-fleuret-nips2010.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:164044","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/164044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:164044","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/164044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},{"id":"mag:2097735973","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/4148-joint-cascade-optimization-using-a-product-of-boosted-classifiers.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:164044","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/164044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1601741105","https://openalex.org/W1984525543","https://openalex.org/W2023014843","https://openalex.org/W2031812579","https://openalex.org/W2099355420","https://openalex.org/W2103142054","https://openalex.org/W2104577112","https://openalex.org/W2113201641","https://openalex.org/W2116445618","https://openalex.org/W2117990954","https://openalex.org/W2123066336","https://openalex.org/W2140274257","https://openalex.org/W2141094784","https://openalex.org/W2146514558","https://openalex.org/W2147474239","https://openalex.org/W2148469355","https://openalex.org/W2151673653","https://openalex.org/W2157176527","https://openalex.org/W2160794449","https://openalex.org/W2161969291","https://openalex.org/W2164598857","https://openalex.org/W2170110077","https://openalex.org/W2534457893","https://openalex.org/W2538008885","https://openalex.org/W2545295063"],"related_works":["https://openalex.org/W3010693587","https://openalex.org/W2759676328","https://openalex.org/W7097401897","https://openalex.org/W2916084847","https://openalex.org/W2613957516","https://openalex.org/W7095107572","https://openalex.org/W2745898864","https://openalex.org/W2794021631","https://openalex.org/W3036900384","https://openalex.org/W2515049322"],"abstract_inverted_index":{"The":[0,17],"standard":[1,140,155],"strategy":[2],"for":[3],"efficient":[4],"object":[5],"detection":[6,18,153],"consists":[7],"of":[8,13,23,27,30,33,43,61,69,75,83,146],"building":[9],"a":[10,24,53,63,70,76,101,105,118,128,139],"cascade":[11,85],"composed":[12],"several":[14],"binary":[15],"classifiers.":[16],"process":[19],"takes":[20],"the":[21,28,31,38,44,59,67,73,80,84,87,91,114,122,135,144],"form":[22],"lazy":[25],"evaluation":[26],"conjunction":[29],"responses":[32],"these":[34],"classifiers,":[35],"and":[36,79,104,133,151,157],"concentrates":[37],"computation":[39],"on":[40,113,127,149],"difficult":[41],"parts":[42],"image":[45],"which":[46,65],"cannot":[47],"be":[48],"trivially":[49],"rejected.":[50],"We":[51,142],"introduce":[52],"novel":[54],"algorithm":[55],"to":[56,108,125,138],"construct":[57],"jointly":[58],"classifiers":[60],"such":[62],"cascade,":[64],"interprets":[66],"response":[68,82],"classifier":[71],"as":[72,86],"probability":[74,88,112],"positive":[77],"prediction,":[78],"overall":[81],"that":[89,110],"all":[90],"predictions":[92],"are":[93],"positive.":[94],"From":[95],"this":[96,147],"noisy-AND":[97],"model,":[98],"we":[99],"derive":[100],"consistent":[102],"loss":[103],"Boosting":[106],"procedure":[107],"optimize":[109],"global":[111],"training":[115],"set.":[116],"Such":[117],"joint":[119],"learning":[120],"allows":[121],"individual":[123],"predictors":[124],"focus":[126],"more":[129],"restricted":[130],"modeling":[131],"problem,":[132],"improves":[134],"performance":[136],"compared":[137],"cascade.":[141],"demonstrate":[143],"efficiency":[145],"approach":[148],"face":[150],"pedestrian":[152],"with":[154,159],"data-sets":[156],"comparisons":[158],"reference":[160],"baselines.":[161],"1":[162]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}