{"id":"https://openalex.org/W2773003563","doi":"https://doi.org/10.1109/iccv.2017.557","title":"Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition","display_name":"Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2773003563","doi":"https://doi.org/10.1109/iccv.2017.557","mag":"2773003563"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2017.557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","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/A5102507347","display_name":"Heliang Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heliang Zheng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["University of Rochester, Rochester, NY"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102507347"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":32.0787,"has_fulltext":false,"cited_by_count":1030,"citation_normalized_percentile":{"value":0.99766435,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5219","last_page":"5227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9908000230789185,"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8261280655860901},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8132405877113342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792872190475464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7663778066635132},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6973448991775513},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6920969486236572},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6847745180130005},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5944486856460571},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5201224088668823},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.47356951236724854},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46498414874076843},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4424609839916229},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4280877113342285},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4277501106262207},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.414492130279541},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36712491512298584},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.29872268438339233},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2725623548030853}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8261280655860901},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8132405877113342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792872190475464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7663778066635132},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6973448991775513},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6920969486236572},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6847745180130005},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5944486856460571},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5201224088668823},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.47356951236724854},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46498414874076843},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4424609839916229},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4280877113342285},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4277501106262207},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.414492130279541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36712491512298584},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29872268438339233},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2725623548030853},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2017.557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W603908379","https://openalex.org/W1432090866","https://openalex.org/W1496650988","https://openalex.org/W1616462885","https://openalex.org/W1686810756","https://openalex.org/W1846799578","https://openalex.org/W1898560071","https://openalex.org/W1925596459","https://openalex.org/W1928906481","https://openalex.org/W1955942245","https://openalex.org/W1958236864","https://openalex.org/W1967632700","https://openalex.org/W2039507552","https://openalex.org/W2049632392","https://openalex.org/W2102605133","https://openalex.org/W2104657103","https://openalex.org/W2138011018","https://openalex.org/W2150856297","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2202499615","https://openalex.org/W2207849498","https://openalex.org/W2213472736","https://openalex.org/W2295107390","https://openalex.org/W2306952455","https://openalex.org/W2398118205","https://openalex.org/W2403585668","https://openalex.org/W2462457117","https://openalex.org/W2479109623","https://openalex.org/W2613763509","https://openalex.org/W2737725206","https://openalex.org/W2950094539","https://openalex.org/W2951538594","https://openalex.org/W2962835968","https://openalex.org/W2964036919","https://openalex.org/W3124951096","https://openalex.org/W4285719527","https://openalex.org/W6600609147","https://openalex.org/W6602324145","https://openalex.org/W6618372016","https://openalex.org/W6636475194","https://openalex.org/W6637373629","https://openalex.org/W6638677478","https://openalex.org/W6640376812","https://openalex.org/W6684191040","https://openalex.org/W6687751829","https://openalex.org/W6698041030","https://openalex.org/W6713467259","https://openalex.org/W6737781455","https://openalex.org/W6790300624"],"related_works":["https://openalex.org/W3192357901","https://openalex.org/W3036286480","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4237171675","https://openalex.org/W3209723314","https://openalex.org/W2952736415","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W2962677013"],"abstract_inverted_index":{"Recognizing":[0],"fine-grained":[1,14,37,123,157,198],"categories":[2],"(e.g.,":[3,31,40],"bird":[4],"species)":[5],"highly":[6],"relies":[7],"on":[8,194],"discriminative":[9,122,149],"part":[10,29,53,64,80,108,141],"localization":[11,30],"and":[12,36,66,79,95,102,140,154,173,189,203],"part-based":[13],"feature":[15,38,67,90,152],"learning.":[16],"Existing":[17],"approaches":[18],"predominantly":[19],"solve":[20],"these":[21],"challenges":[22],"independently,":[23],"while":[24],"neglecting":[25],"the":[26,134,180,191],"fact":[27],"that":[28],"head":[32,41],"of":[33,75,137],"a":[34,51,57,162],"bird)":[35],"learning":[39,54,68,136],"shape)":[42],"are":[43,130],"mutually":[44],"correlated.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"novel":[52],"approach":[55],"by":[56,99,115],"multi-attention":[58],"convolutional":[59,93],"neural":[60],"network":[61,86,110],"(MA-CNN),":[62],"where":[63],"generation":[65],"can":[69,125,174],"reinforce":[70],"each":[71,116],"other.":[72],"MA-CNN":[73,145,166,184],"consists":[74],"convolution,":[76],"channel":[77,84,138],"grouping":[78,85,139],"classification":[81,109],"sub-networks.":[82],"The":[83,107],"takes":[87],"as":[88],"input":[89],"channels":[91,153],"from":[92,104,151,159,183],"layers,":[94],"generates":[96],"multiple":[97],"parts":[98,150,160,182],"clustering,":[100],"weighting":[101],"pooling":[103],"spatially-correlated":[105],"channels.":[106],"further":[111],"classifies":[112],"an":[113],"image":[114],"individual":[117],"part,":[118],"through":[119],"which":[120,143],"more":[121,148],"features":[124,158],"be":[126,175],"learned.":[127],"Two":[128],"losses":[129],"proposed":[131],"to":[132,146],"guide":[133],"multi-task":[135],"classification,":[142],"encourages":[144],"generate":[147],"learn":[155],"better":[156],"in":[161],"mutual":[163],"reinforced":[164],"way.":[165],"does":[167],"not":[168],"need":[169],"bounding":[170],"box/part":[171],"annotation":[172],"trained":[176],"end-to-end.":[177],"We":[178],"incorporate":[179],"learned":[181],"with":[185],"part-CNN":[186],"for":[187],"recognition,":[188],"show":[190],"best":[192],"performances":[193],"three":[195],"challenging":[196],"published":[197],"datasets,":[199],"e.g.,":[200],"CUB-Birds,":[201],"FGVC-Aircraft":[202],"Stanford-Cars.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":67},{"year":2024,"cited_by_count":117},{"year":2023,"cited_by_count":146},{"year":2022,"cited_by_count":127},{"year":2021,"cited_by_count":218},{"year":2020,"cited_by_count":158},{"year":2019,"cited_by_count":123},{"year":2018,"cited_by_count":65},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}