{"id":"https://openalex.org/W1984753744","doi":"https://doi.org/10.1109/icip.2011.6115811","title":"Multimodal learning for multi-label image classification","display_name":"Multimodal learning for multi-label image classification","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W1984753744","doi":"https://doi.org/10.1109/icip.2011.6115811","mag":"1984753744"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2011.6115811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2011.6115811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 18th IEEE International Conference on Image Processing","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/A5086887025","display_name":"Yanwei Pang","orcid":"https://orcid.org/0000-0001-6670-3727"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["Department of Electrical Information Engineering, Tianjin University, TJU, Tianjin, China","Department of Electrical Information Engineering, Tianjin University, Tianjin 300072, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Information Engineering, Tianjin University, TJU, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Department of Electrical Information Engineering, Tianjin University, Tianjin 300072, P. R. China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101872394","display_name":"Zhao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Ma","raw_affiliation_strings":["Department of Electrical Information Engineering, Tianjin University, TJU, Tianjin, China","Department of Electrical Information Engineering, Tianjin University, Tianjin 300072, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Information Engineering, Tianjin University, TJU, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Department of Electrical Information Engineering, Tianjin University, Tianjin 300072, P. R. China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334733","display_name":"Yuan Yuan","orcid":"https://orcid.org/0000-0001-7964-6514"},"institutions":[{"id":"https://openalex.org/I4210144662","display_name":"Xi'an Institute of Optics and Precision Mechanics","ror":"https://ror.org/0444j5556","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210144662"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Yuan","raw_affiliation_strings":["Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, Shaanxi, China","Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119 Shaanxi, P. R. China"],"affiliations":[{"raw_affiliation_string":"Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I4210144662"]},{"raw_affiliation_string":"Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119 Shaanxi, P. R. China","institution_ids":["https://openalex.org/I4210144662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740143","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0002-0019-4197"},"institutions":[{"id":"https://openalex.org/I4210144662","display_name":"Xi'an Institute of Optics and Precision Mechanics","ror":"https://ror.org/0444j5556","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210144662"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, Shaanxi, China","Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119 Shaanxi, P. R. China"],"affiliations":[{"raw_affiliation_string":"Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I4210144662"]},{"raw_affiliation_string":"Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119 Shaanxi, P. R. China","institution_ids":["https://openalex.org/I4210144662"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012311011","display_name":"Kongqiao Wang","orcid":"https://orcid.org/0000-0002-2214-5062"},"institutions":[{"id":"https://openalex.org/I4210099903","display_name":"Nokia (China)","ror":"https://ror.org/01607kg94","country_code":"CN","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210099903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kongqiao Wang","raw_affiliation_strings":["Nokia Research Center, Beijing, China","Nokia Research Center Beijing, Beijing 100176, P. R. China"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210099903"]},{"raw_affiliation_string":"Nokia Research Center Beijing, Beijing 100176, P. R. China","institution_ids":["https://openalex.org/I4210099903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086887025"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.7841,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.7411156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1797","last_page":"1800"},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9972000122070312,"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/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.9116373062133789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7819571495056152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6289176940917969},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5988408327102661},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.546094536781311},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5301638245582581},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.5175782442092896},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4950961172580719},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4533079266548157},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.440449059009552},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42267102003097534},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4178028404712677},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4131971001625061},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.41034454107284546},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4064645767211914},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4042724668979645},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.362691193819046},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.3079755902290344}],"concepts":[{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.9116373062133789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819571495056152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6289176940917969},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5988408327102661},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.546094536781311},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5301638245582581},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.5175782442092896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4950961172580719},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4533079266548157},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.440449059009552},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42267102003097534},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4178028404712677},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4131971001625061},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.41034454107284546},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4064645767211914},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4042724668979645},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.362691193819046},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3079755902290344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip.2011.6115811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2011.6115811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 18th IEEE International Conference on Image Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.bbk.ac.uk.oai2:7378","is_oa":false,"landing_page_url":"https://eprints.bbk.ac.uk/id/eprint/7378/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400466","display_name":"BIROn (Birkbeck, University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98259816","host_organization_name":"Birkbeck, University of London","host_organization_lineage":["https://openalex.org/I98259816"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1981613567","https://openalex.org/W2042759724","https://openalex.org/W2066058128","https://openalex.org/W2106503792","https://openalex.org/W2119821739","https://openalex.org/W2125263373","https://openalex.org/W2134731454","https://openalex.org/W2151103935","https://openalex.org/W2155803963","https://openalex.org/W2536627426","https://openalex.org/W4239510810","https://openalex.org/W6645417777","https://openalex.org/W6678960507","https://openalex.org/W6728672506"],"related_works":["https://openalex.org/W2158102958","https://openalex.org/W2086564093","https://openalex.org/W1995462736","https://openalex.org/W2938717424","https://openalex.org/W2028757524","https://openalex.org/W2548286644","https://openalex.org/W2009049007","https://openalex.org/W2389814472","https://openalex.org/W1970129632","https://openalex.org/W4365503698"],"abstract_inverted_index":{"We":[0],"tackle":[1],"the":[2,18,40,83,98],"challenge":[3],"of":[4,20,85,100],"web":[5],"image":[6,68,91,101],"classification":[7,116],"using":[8,86],"additional":[9],"tags":[10,112],"information.":[11],"Unlike":[12],"traditional":[13],"methods":[14],"that":[15,96,121],"only":[16],"use":[17,27,53],"combination":[19],"several":[21,123],"low-level":[22,124],"features,":[23],"we":[24,38,81,94],"try":[25],"to":[26,30,58,64,89,107],"semantic":[28,47,105],"concepts":[29],"represent":[31,108],"images":[32,109],"and":[33,51,61,77,110],"corresponding":[34],"tags.":[35],"At":[36],"first,":[37],"extract":[39],"latent":[41,46,104],"topic":[42],"information":[43],"by":[44],"probabilistic":[45],"analysis":[48],"(pLSA)":[49],"algorithm,":[50],"then":[52],"multi-label":[54],"multiple":[55],"kernel":[56],"learning":[57],"combine":[59],"visual":[60],"textual":[62],"features":[63],"make":[65],"a":[66],"better":[67,115],"classification.":[69,92],"In":[70],"our":[71],"experiments":[72],"on":[73,97],"PASCAL":[74],"VOC'07":[75],"set":[76],"MIR":[78],"Flickr":[79],"set,":[80],"demonstrate":[82],"benefit":[84],"multimodal":[87],"feature":[88,106],"improve":[90],"Specifically,":[93],"discover":[95],"issue":[99],"classification,":[102],"utilizing":[103],"associated":[111],"can":[113],"obtain":[114],"results":[117],"than":[118],"other":[119],"ways":[120],"integrating":[122],"features.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}