{"id":"https://openalex.org/W2460852148","doi":"https://doi.org/10.1109/tmm.2017.2648498","title":"Diversified Visual Attention Networks for Fine-Grained Object Classification","display_name":"Diversified Visual Attention Networks for Fine-Grained Object Classification","publication_year":2017,"publication_date":"2017-01-05","ids":{"openalex":"https://openalex.org/W2460852148","doi":"https://doi.org/10.1109/tmm.2017.2648498","mag":"2460852148"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2017.2648498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2017.2648498","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1606.08572","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bo Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wu","raw_affiliation_strings":["School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiashi Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiashi Feng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiang Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Peng","raw_affiliation_strings":["School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shuicheng Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4800084"],"apc_list":null,"apc_paid":null,"fwci":14.2342,"has_fulltext":false,"cited_by_count":363,"citation_normalized_percentile":{"value":0.99196596,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"19","issue":"6","first_page":"1245","last_page":"1256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6047000288963318,"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":0.6047000288963318,"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":0.22269999980926514,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.022099999710917473,"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/discriminative-model","display_name":"Discriminative model","score":0.9190999865531921},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5853000283241272},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5489000082015991},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5142999887466431},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.5055999755859375},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49619999527931213},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4733999967575073},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.396699994802475},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3808000087738037}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9190999865531921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7738000154495239},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5853000283241272},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5142999887466431},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.5055999755859375},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4749000072479248},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.36640000343322754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3280999958515167},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C58103923","wikidata":"https://www.wikidata.org/wiki/Q2286025","display_name":"Silhouette","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.2614000141620636},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2017.2648498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2017.2648498","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1606.08572","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.08572","pdf_url":"https://arxiv.org/pdf/1606.08572","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1606.08572","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.08572","pdf_url":"https://arxiv.org/pdf/1606.08572","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4658455102","display_name":null,"funder_award_id":"61373121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4723142613","display_name":null,"funder_award_id":"61328205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6002393728","display_name":null,"funder_award_id":"201507000032","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1496650988","https://openalex.org/W1567302070","https://openalex.org/W1847551302","https://openalex.org/W1905692714","https://openalex.org/W1958236864","https://openalex.org/W1967632700","https://openalex.org/W1981333244","https://openalex.org/W1995525705","https://openalex.org/W1995543189","https://openalex.org/W2014102544","https://openalex.org/W2049248196","https://openalex.org/W2064675550","https://openalex.org/W2088049833","https://openalex.org/W2091759811","https://openalex.org/W2101298495","https://openalex.org/W2102605133","https://openalex.org/W2104657103","https://openalex.org/W2115091888","https://openalex.org/W2118696714","https://openalex.org/W2122710056","https://openalex.org/W2135706578","https://openalex.org/W2138011018","https://openalex.org/W2155839910","https://openalex.org/W2200631819","https://openalex.org/W2313077179","https://openalex.org/W2409991892","https://openalex.org/W2618530766","https://openalex.org/W4241811150","https://openalex.org/W6602324145","https://openalex.org/W6618372016","https://openalex.org/W6628927728","https://openalex.org/W6630875275","https://openalex.org/W6631760426","https://openalex.org/W6635446068","https://openalex.org/W6636475194","https://openalex.org/W6637373629","https://openalex.org/W6637556369","https://openalex.org/W6638319203","https://openalex.org/W6638667902","https://openalex.org/W6640376812","https://openalex.org/W6646201289","https://openalex.org/W6648737282","https://openalex.org/W6651233513","https://openalex.org/W6675541922","https://openalex.org/W6675696936","https://openalex.org/W6677700107","https://openalex.org/W6682137061","https://openalex.org/W6682778277","https://openalex.org/W6684876274","https://openalex.org/W6684983439","https://openalex.org/W6696078910","https://openalex.org/W6696270381","https://openalex.org/W6698041030","https://openalex.org/W6721588977"],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"object":[1,89,165],"classification":[2,177],"attracts":[3],"increasing":[4],"attention":[5,28,59,64,80,118,131,154],"in":[6,58,68,229],"multimedia":[7],"applications.":[8],"However,":[9],"it":[10],"is":[11,120,145,178],"a":[12,77,172],"quite":[13],"challenging":[14],"problem":[15,86],"due":[16],"to":[17,33,83,102,122,126,135,147,162,168,215],"the":[18,36,56,85,94,115,127,149,160,164,184,192,208,216],"subtle":[19],"interclass":[20],"difference":[21],"and":[22,119,151,171,189,201,231],"large":[23],"intraclass":[24],"variation.":[25],"Recently,":[26],"visual":[27,79],"models":[29,65],"have":[30,48,205],"been":[31],"applied":[32],"automatically":[34],"localize":[35,103],"discriminative":[37,104,124],"regions":[38,105],"of":[39,55,62,87,117,153,191],"an":[40],"image":[41],"for":[42,100,139,176],"better":[43],"capturing":[44],"critical":[45],"difference,":[46],"which":[47,91],"demonstrated":[49,206],"promising":[50],"performance.":[51],"Unfortunately,":[52],"without":[53,219],"consideration":[54],"diversity":[57,116],"process,":[60],"most":[61],"existing":[63],"perform":[66],"poorly":[67],"classifying":[69],"fine-grained":[70,88],"objects.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"propose":[76],"diversified":[78],"network":[81],"(DVAN)":[82],"address":[84],"classification,":[90],"substantially":[92],"relieves":[93],"dependency":[95],"on":[96,197],"strongly":[97],"supervised":[98],"information":[99,125,185],"learning":[101],"compared":[106,214],"with":[107],"attention-less":[108],"models.":[109],"More":[110],"importantly,":[111],"DVAN":[112,158,210],"explicitly":[113],"pursues":[114],"able":[121],"gather":[123],"maximal":[128],"extent.":[129],"Multiple":[130],"canvases":[132],"are":[133],"generated":[134],"extract":[136],"convolutional":[137],"features":[138],"attention.":[140],"An":[141],"LSTM":[142],"recurrent":[143],"unit":[144],"employed":[146],"learn":[148],"attentiveness":[150],"discrimination":[152],"canvases.":[155],"The":[156],"proposed":[157],"has":[159],"ability":[161],"attend":[163],"from":[166,186],"coarse":[167],"fine":[169],"granularity,":[170],"dynamic":[173],"internal":[174],"representation":[175],"built":[179],"up":[180],"by":[181],"incrementally":[182],"combining":[183],"different":[187],"locations":[188],"scales":[190],"image.":[193],"Extensive":[194],"experiments":[195],"conducted":[196],"CUB-2011,":[198],"Stanford":[199,202],"Dogs,":[200],"Cars":[203],"datasets":[204],"that":[207],"pro-posed":[209],"achieves":[211],"competitive":[212],"performance":[213],"state-of-the-art":[217],"approaches,":[218],"using":[220],"any":[221],"prior":[222],"knowledge,":[223],"user":[224],"interaction,":[225],"or":[226],"external":[227],"resource":[228],"training":[230],"testing.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":57},{"year":2021,"cited_by_count":54},{"year":2020,"cited_by_count":64},{"year":2019,"cited_by_count":59},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2016-07-22T00:00:00"}