{"id":"https://openalex.org/W2016016818","doi":"https://doi.org/10.1109/cvpr.2014.309","title":"Multi-fold MIL Training for Weakly Supervised Object Localization","display_name":"Multi-fold MIL Training for Weakly Supervised Object Localization","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W2016016818","doi":"https://doi.org/10.1109/cvpr.2014.309","mag":"2016016818"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2014.309","doi":"https://doi.org/10.1109/cvpr.2014.309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2014.309","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2016016818"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00975746","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051499142","display_name":"Ramazan G\u00f6kberk Cinbi\u015f","orcid":"https://orcid.org/0000-0003-0962-7101","observed_orcids":["https://orcid.org/0000-0003-0962-7101"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210149092","display_name":"Laboratoire Jean Kuntzmann","ror":"https://ror.org/04ett5b41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210149092","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ramazan Gokberk Cinbis","raw_affiliation_strings":["LEAR team, Laboratoire Jean Kuntz-mann, CNRS, Univ. Grenoble Alpes, France","Learning and recognition in vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LEAR team, Laboratoire Jean Kuntz-mann, CNRS, Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210149092","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Learning and recognition in vision","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040312210","display_name":"Jakob Jozef Verbeek","orcid":"https://orcid.org/0000-0003-1419-1816","observed_orcids":["https://orcid.org/0000-0003-1419-1816"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210149092","display_name":"Laboratoire Jean Kuntzmann","ror":"https://ror.org/04ett5b41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210149092","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jakob Verbeek","raw_affiliation_strings":["LEAR team, Laboratoire Jean Kuntz-mann, CNRS, Univ. Grenoble Alpes, France","Learning and recognition in vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LEAR team, Laboratoire Jean Kuntz-mann, CNRS, Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210149092","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Learning and recognition in vision","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":"https://orcid.org/0009-0005-7239-3741","observed_orcids":["https://orcid.org/0009-0005-7239-3741"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210149092","display_name":"Laboratoire Jean Kuntzmann","ror":"https://ror.org/04ett5b41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210149092","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["LEAR team, Laboratoire Jean Kuntz-mann, CNRS, Univ. Grenoble Alpes, France","Learning and recognition in vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LEAR team, Laboratoire Jean Kuntz-mann, CNRS, Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210149092","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Learning and recognition in vision","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.9262,"has_fulltext":false,"cited_by_count":219,"citation_normalized_percentile":{"value":0.99457148,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2409","last_page":"2416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5396000146865845,"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":0.5396000146865845,"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":0.4325999915599823,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.010400000028312206,"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/weakly-supervised-object-localization","display_name":"weakly supervised object localization","score":0.9300000071525574},{"id":"https://openalex.org/keywords/multiple-instance-learning","display_name":"multiple instance learning","score":0.8090000152587891},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.4909999966621399},{"id":"https://openalex.org/keywords/fisher-vectors","display_name":"Fisher vectors","score":0.7440000176429749},{"id":"https://openalex.org/keywords/bounding-box-annotation","display_name":"bounding box annotation","score":0.4690000116825104},{"id":"https://openalex.org/keywords/pascal-voc-2007","display_name":"Pascal VOC 2007","score":0.8019999861717224}],"concepts":[{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.846481204032898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7721714973449707},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6784461736679077},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6658896207809448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591883897781372},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6353380084037781},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5983380675315857},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5887404084205627},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5861191749572754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49978184700012207},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4863165318965912},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4675525426864624},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4456096291542053},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4185553193092346},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39166632294654846},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2864200472831726},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12718328833580017},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09988996386528015},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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":7,"locations":[{"id":"doi:10.1109/cvpr.2014.309","doi":"https://doi.org/10.1109/cvpr.2014.309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2014.309","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00975746v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00975746","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2014, Columbus, United States. pp.2409-2416, ⟨10.1109/CVPR.2014.309⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:https://open.metu.edu.tr:11511/57653","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11511/57653","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.635.9554","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.635.9554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.univ-grenoble-alpes.fr/docs/00/97/57/46/PDF/paper.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.657.1349","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.657.1349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-00975746/PDF/paper.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.800.1739","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.800.1739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/97/57/46/PDF/paper.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.934.3054","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.934.3054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Cinbis_Multi-fold_MIL_Training_2014_CVPR_paper.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00975746v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00975746","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2014, Columbus, United States. pp.2409-2416, ⟨10.1109/CVPR.2014.309⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W25437484","https://openalex.org/W1552060966","https://openalex.org/W1575299770","https://openalex.org/W1590510366","https://openalex.org/W1603728330","https://openalex.org/W1880262756","https://openalex.org/W1966385142","https://openalex.org/W1973054923","https://openalex.org/W1976921161","https://openalex.org/W2001709803","https://openalex.org/W2020477327","https://openalex.org/W2027953712","https://openalex.org/W2031489346","https://openalex.org/W2037511607","https://openalex.org/W2039507552","https://openalex.org/W2061629163","https://openalex.org/W2079267072","https://openalex.org/W2088049833","https://openalex.org/W2099528205","https://openalex.org/W2106874006","https://openalex.org/W2107200795","https://openalex.org/W2107558380","https://openalex.org/W2110119381","https://openalex.org/W2112343299","https://openalex.org/W2120369594","https://openalex.org/W2123023145","https://openalex.org/W2127453602","https://openalex.org/W2128715914","https://openalex.org/W2130350952","https://openalex.org/W2137023887","https://openalex.org/W2138761194","https://openalex.org/W2168356304","https://openalex.org/W4237791300"],"related_works":["https://openalex.org/W2133324800","https://openalex.org/W2401196401","https://openalex.org/W3034329658","https://openalex.org/W2946279720","https://openalex.org/W2290280043","https://openalex.org/W2895038424","https://openalex.org/W4387969676","https://openalex.org/W2737326572","https://openalex.org/W3180266489","https://openalex.org/W2061629163"],"abstract_inverted_index":{"Object":[0],"category":[1],"localization":[2],"is":[3,24,36,78,97],"a":[4,56,79,112],"challenging":[5],"problem":[6],"in":[7,26,48,70,133],"computer":[8],"vision.":[9],"Standard":[10],"supervised":[11,28,34,126],"training":[12,73,87,135],"requires":[13],"bounding":[14],"box":[15],"annotations":[16],"of":[17,45],"object":[18,46,68,93],"instances.":[19],"This":[20,95],"time-consuming":[21],"annotation":[22],"process":[23],"sidestepped":[25],"weakly":[27,125],"learning.":[29],"In":[30],"this":[31],"case,":[32],"the":[33,43,49,63,67,71,105,117,134],"information":[35],"restricted":[37],"to":[38,123],"binary":[39],"labels":[40],"that":[41,60],"indicate":[42],"absence/presence":[44],"instances":[47],"image,":[50],"without":[51],"their":[52],"locations.":[53,94],"We":[54,110],"follow":[55],"multiple-instance":[57],"learning":[58,83],"approach":[59,129],"iteratively":[61],"trains":[62],"detector":[64],"and":[65],"infers":[66],"locations":[69],"positive":[72],"images.":[74],"Our":[75],"main":[76],"contribution":[77],"multi-fold":[80],"multiple":[81],"instance":[82],"procedure,":[84],"which":[85,137],"prevents":[86],"from":[88],"prematurely":[89],"locking":[90],"onto":[91],"erroneous":[92],"procedure":[96],"particularly":[98],"important":[99],"when":[100],"high-dimensional":[101],"representations,":[102],"such":[103],"as":[104],"Fisher":[106],"vectors,":[107],"are":[108],"used.":[109],"present":[111],"detailed":[113],"experimental":[114],"evaluation":[115],"using":[116],"PASCAL":[118],"VOC":[119],"2007":[120],"dataset.":[121],"Compared":[122],"state-of-the-art":[124],"detectors,":[127],"our":[128],"better":[130],"localizes":[131],"objects":[132],"images,":[136],"translates":[138],"into":[139],"improved":[140],"detection":[141],"performance.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":32},{"year":2017,"cited_by_count":36},{"year":2016,"cited_by_count":35},{"year":2015,"cited_by_count":21},{"year":2014,"cited_by_count":5}],"updated_date":"2026-11-15T12:55:33.944570","created_date":"2016-06-24T00:00:00"}