{"id":"https://openalex.org/W1973054923","doi":"https://doi.org/10.1109/cvpr.2012.6248065","title":"Learning object class detectors from weakly annotated video","display_name":"Learning object class detectors from weakly annotated video","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W1973054923","doi":"https://doi.org/10.1109/cvpr.2012.6248065","mag":"1973054923"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2012.6248065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6248065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00695940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006270674","display_name":"Alessandro Prest","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Alessandro Prest","raw_affiliation_strings":["ETH Zurich, Switzerland","Eidgen\u00f6ssische Technische Hochschule - Swiss Federal Institute of Technology  [Z\u00fcrich]","Learning and recognition in vision"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Eidgen\u00f6ssische Technische Hochschule - Swiss Federal Institute of Technology  [Z\u00fcrich]","institution_ids":[]},{"raw_affiliation_string":"Learning and recognition in vision","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088003216","display_name":"Christian Leistner","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"C. Leistner","raw_affiliation_strings":["ETH Zurich, Switzerland","Eidgen\u00f6ssische Technische Hochschule - Swiss Federal Institute of Technology  [Z\u00fcrich]"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Eidgen\u00f6ssische Technische Hochschule - Swiss Federal Institute of Technology  [Z\u00fcrich]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077355742","display_name":"Javier Civera","orcid":"https://orcid.org/0000-0003-1368-1151"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"J. Civera","raw_affiliation_strings":["Universidad de Zaragoza, Spain","Departamento de Inform\u00e1tica e Ingenier\u00eda de Sistemas"],"affiliations":[{"raw_affiliation_string":"Universidad de Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]},{"raw_affiliation_string":"Departamento de Inform\u00e1tica e Ingenier\u00eda de Sistemas","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110279104","display_name":"C. Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Schmid","raw_affiliation_strings":["INRIA Grenoble, France","Learning and recognition in vision"],"affiliations":[{"raw_affiliation_string":"INRIA Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Learning and recognition in vision","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003940396","display_name":"Vittorio Ferrari","orcid":"https://orcid.org/0000-0002-3949-9975"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"V. Ferrari","raw_affiliation_strings":["University of Edinburgh, UK","Eidgen\u00f6ssische Technische Hochschule - Swiss Federal Institute of Technology  [Z\u00fcrich]"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Eidgen\u00f6ssische Technische Hochschule - Swiss Federal Institute of Technology  [Z\u00fcrich]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006270674"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":38.0114,"has_fulltext":false,"cited_by_count":479,"citation_normalized_percentile":{"value":0.99820112,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3282","last_page":"3289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983000159263611,"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":0.8317281007766724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7812669277191162},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6895071268081665},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6645334959030151},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6205358505249023},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5829480886459351},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5805148482322693},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5681432485580444},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5078807473182678},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.470502108335495},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46053269505500793},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4518267512321472},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4022877812385559},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15631341934204102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317281007766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7812669277191162},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6895071268081665},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6645334959030151},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6205358505249023},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5829480886459351},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5805148482322693},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5681432485580444},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5078807473182678},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.470502108335495},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46053269505500793},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4518267512321472},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4022877812385559},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15631341934204102},{"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":4,"locations":[{"id":"doi:10.1109/cvpr.2012.6248065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6248065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.6563","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.6563","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/00/71/35/68/PDF/VO.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.659.3413","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.659.3413","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-00695940/document/","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00695940v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00695940","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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 2012 - Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, RI, United States. pp.3282-3289, ⟨10.1109/CVPR.2012.6248065⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00695940v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00695940","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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 2012 - Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, RI, United States. pp.3282-3289, ⟨10.1109/CVPR.2012.6248065⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1496571393","https://openalex.org/W1552060966","https://openalex.org/W1566135517","https://openalex.org/W1677409904","https://openalex.org/W1952794764","https://openalex.org/W1971293974","https://openalex.org/W1988348003","https://openalex.org/W2027953712","https://openalex.org/W2031342017","https://openalex.org/W2073983104","https://openalex.org/W2087515439","https://openalex.org/W2095581372","https://openalex.org/W2099528205","https://openalex.org/W2105148880","https://openalex.org/W2105842272","https://openalex.org/W2112565353","https://openalex.org/W2119605622","https://openalex.org/W2120369594","https://openalex.org/W2122156965","https://openalex.org/W2128715914","https://openalex.org/W2134380836","https://openalex.org/W2134529554","https://openalex.org/W2142173439","https://openalex.org/W2147533695","https://openalex.org/W2154422044","https://openalex.org/W2154683974","https://openalex.org/W2156689847","https://openalex.org/W2161969291","https://openalex.org/W2162915993","https://openalex.org/W2164598857","https://openalex.org/W2164918853","https://openalex.org/W2165698076","https://openalex.org/W2168356304","https://openalex.org/W2170865122","https://openalex.org/W2534457893","https://openalex.org/W2538008885","https://openalex.org/W6629607343","https://openalex.org/W6633236808","https://openalex.org/W6640860105","https://openalex.org/W6675783020","https://openalex.org/W6680770976","https://openalex.org/W6684705394"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W1689909837","https://openalex.org/W2953362004","https://openalex.org/W4298525700"],"abstract_inverted_index":{"Object":[0],"detectors":[1,23],"are":[2],"typically":[3],"trained":[4,160],"on":[5,67,93],"a":[6,34,39,47,56,120,131,140,158],"large":[7],"set":[8,48],"of":[9,33,49,51,86,113,142,157],"still":[10,94,116,149,162],"images":[11,117,150,163],"annotated":[12,144,148],"by":[13,119],"bounding-boxes.":[14],"This":[15],"paper":[16],"introduces":[17],"an":[18],"approach":[19,61],"for":[20,58],"learning":[21,127],"object":[22],"from":[24,105,128,139,161],"real-world":[25],"web":[26,106],"videos":[27,50,107,129,145],"known":[28],"only":[29],"to":[30,83,115],"contain":[31],"objects":[32,45],"target":[35],"class.":[36],"We":[37,100,135],"propose":[38],"fully":[40,147],"automatic":[41],"pipeline":[42],"that":[43,102,137],"localizes":[44],"in":[46,111],"the":[52,84,87,126,155],"class":[53],"and":[54,70,146],"learns":[55],"detector":[57,92,159],"it.":[59],"The":[60],"extracts":[62],"candidate":[63],"spatio-temporal":[64],"tubes":[65],"based":[66],"motion":[68],"segmentation":[69],"then":[71],"selects":[72],"one":[73],"tube":[74],"per":[75],"video":[76],"jointly":[77],"over":[78],"all":[79],"videos.":[80],"To":[81],"compare":[82],"state":[85],"art,":[88],"we":[89,124],"test":[90],"our":[91],"images,":[95],"i.e.,":[96],"Pascal":[97],"VOC":[98],"2007.":[99],"observe":[101],"frames":[103],"extracted":[104],"can":[108],"differ":[109],"significantly":[110],"terms":[112],"quality":[114],"taken":[118],"good":[121],"camera.":[122],"Thus,":[123],"formulate":[125],"as":[130],"domain":[132,152],"adaptation":[133,153],"task.":[134],"show":[136],"training":[138],"combination":[141],"weakly":[143],"using":[151],"improves":[154],"performance":[156],"alone.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":60},{"year":2018,"cited_by_count":54},{"year":2017,"cited_by_count":65},{"year":2016,"cited_by_count":65},{"year":2015,"cited_by_count":38},{"year":2014,"cited_by_count":35},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}