{"id":"https://openalex.org/W2541843346","doi":"https://doi.org/10.1109/iccv.2009.5459194","title":"Joint learning of visual attributes, object classes and visual saliency","display_name":"Joint learning of visual attributes, object classes and visual saliency","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2541843346","doi":"https://doi.org/10.1109/iccv.2009.5459194","mag":"2541843346"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2009.5459194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2009.5459194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 12th International Conference on Computer Vision","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/A5100618174","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-3099-5913"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010851725","display_name":"David Forsyth","orcid":"https://orcid.org/0000-0002-2278-0752"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D Forsyth","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100618174"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":14.2371,"has_fulltext":false,"cited_by_count":149,"citation_normalized_percentile":{"value":0.99158668,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","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"}},"topics":[{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987000226974487,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7548106908798218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.725328803062439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6707316637039185},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6205968856811523},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5434392690658569},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44584667682647705},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12025675177574158}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7548106908798218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.725328803062439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6707316637039185},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6205968856811523},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5434392690658569},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44584667682647705},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12025675177574158},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2009.5459194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2009.5459194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 12th International Conference on Computer Vision","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W123418247","https://openalex.org/W1484228140","https://openalex.org/W1584193343","https://openalex.org/W2035720976","https://openalex.org/W2048679005","https://openalex.org/W2098083083","https://openalex.org/W2098411764","https://openalex.org/W2108745803","https://openalex.org/W2119823327","https://openalex.org/W2120419212","https://openalex.org/W2125560515","https://openalex.org/W2134270519","https://openalex.org/W2145201922","https://openalex.org/W2154422044","https://openalex.org/W2154683974","https://openalex.org/W2160978182","https://openalex.org/W2161969291","https://openalex.org/W2162915993","https://openalex.org/W2186094539","https://openalex.org/W3143107425","https://openalex.org/W6605001058","https://openalex.org/W6634846276","https://openalex.org/W6674700266","https://openalex.org/W6676245398","https://openalex.org/W6678800043"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"We":[0,19,32,138,147],"present":[1],"a":[2,46,52],"method":[3,111],"to":[4,44,68],"learn":[5],"visual":[6],"attributes":[7],"(eg.\u201cred\u201d,":[8],"\u201cmetal\u201d,":[9],"\u201cspotted\u201d)":[10],"and":[11,79,130],"object":[12,60,78],"classes":[13],"(eg.":[14],"\u201ccar\u201d,":[15],"\u201cdress\u201d,":[16],"\u201cumbrella\u201d)":[17],"together.":[18],"assume":[20],"images":[21,119],"are":[22,66],"labeled":[23],"with":[24,35,51,72],"category,":[25],"but":[26],"not":[27,156],"location,":[28],"of":[29,88,97,105,118,120],"an":[30,36,89],"instance.":[31],"estimate":[33],"models":[34,71,81,100],"iterative":[37],"procedure:":[38],"the":[39,59,77,85,94,98,103,106,126,131],"current":[40],"model":[41],"is":[42,112,128,136],"used":[43,67],"produce":[45,69],"saliency":[47],"score,":[48],"which,":[49],"together":[50],"homogeneity":[53],"cue,":[54],"identifies":[55],"likely":[56],"locations":[57,65,87],"for":[58],"(resp.":[61],"attribute);":[62],"then":[63],"those":[64],"better":[70],"multiple":[73],"instance":[74],"learning.":[75],"Crucially,":[76],"attribute":[80,127],"must":[82],"agree":[83],"on":[84,114],"potential":[86],"object.":[90],"This":[91],"means":[92],"that":[93,140],"more":[95],"accurate":[96,108],"two":[99,115],"can":[101],"guide":[102],"improvement":[104,166],"less":[107],"model.":[109],"Our":[110],"evaluated":[113],"data":[116],"sets":[117],"real":[121],"scenes,":[122],"one":[123],"in":[124,133,158,167],"which":[125,134,154],"color":[129],"other":[132],"it":[135],"material.":[137],"show":[139],"our":[141,159],"joint":[142],"learning":[143],"produces":[144],"improved":[145],"detectors.":[146],"demonstrate":[148],"generalization":[149],"by":[150],"detecting":[151],"attribute-object":[152],"pairs":[153],"do":[155],"appear":[157],"training":[160],"data.":[161],"The":[162],"iteration":[163],"gives":[164],"significant":[165],"performance.":[168]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":22},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":16}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}