{"id":"https://openalex.org/W4321780048","doi":"https://doi.org/10.1109/tcsvt.2023.3248791","title":"Dual Transformer With Multi-Grained Assembly for Fine-Grained Visual Classification","display_name":"Dual Transformer With Multi-Grained Assembly for Fine-Grained Visual Classification","publication_year":2023,"publication_date":"2023-02-24","ids":{"openalex":"https://openalex.org/W4321780048","doi":"https://doi.org/10.1109/tcsvt.2023.3248791"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3248791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3248791","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5090452591","display_name":"Ruyi Ji","orcid":"https://orcid.org/0000-0001-8918-0981"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruyi Ji","raw_affiliation_strings":["State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404209","display_name":"Jiaying Li","orcid":"https://orcid.org/0000-0002-2132-3330"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaying Li","raw_affiliation_strings":["School of Computer Science, Beijing Information Science and Technology University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337161","display_name":"Libo Zhang","orcid":"https://orcid.org/0000-0001-8450-0958"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Zhang","raw_affiliation_strings":["State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103449486","display_name":"Yanjun Wu","orcid":"https://orcid.org/0009-0007-4954-8658"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjun Wu","raw_affiliation_strings":["State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090452591"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":4.3013,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95664544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"33","issue":"9","first_page":"5009","last_page":"5021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699587345123291},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5962283611297607},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5796639323234558},{"id":"https://openalex.org/keywords/dual-layer","display_name":"Dual layer","score":0.5769635438919067},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5102524757385254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47887176275253296},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4372231364250183},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.414247065782547},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.23492151498794556},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13539454340934753},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0891914963722229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699587345123291},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5962283611297607},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5796639323234558},{"id":"https://openalex.org/C2993148961","wikidata":"https://www.wikidata.org/wiki/Q5294","display_name":"Dual layer","level":3,"score":0.5769635438919067},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5102524757385254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47887176275253296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4372231364250183},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.414247065782547},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.23492151498794556},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13539454340934753},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0891914963722229},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3248791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3248791","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3056771959","display_name":null,"funder_award_id":"2020111","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G7266047223","display_name":null,"funder_award_id":"ZDBSLY-JSC038","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W1954152232","https://openalex.org/W1955942245","https://openalex.org/W2104657103","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2460852148","https://openalex.org/W2462457117","https://openalex.org/W2737725206","https://openalex.org/W2761785940","https://openalex.org/W2773003563","https://openalex.org/W2797977484","https://openalex.org/W2798381792","https://openalex.org/W2798405286","https://openalex.org/W2809378559","https://openalex.org/W2883502031","https://openalex.org/W2889469641","https://openalex.org/W2891951760","https://openalex.org/W2907110086","https://openalex.org/W2912406707","https://openalex.org/W2945556069","https://openalex.org/W2963225012","https://openalex.org/W2963393555","https://openalex.org/W2963407932","https://openalex.org/W2982512212","https://openalex.org/W2997300818","https://openalex.org/W2997426000","https://openalex.org/W2998345525","https://openalex.org/W2998619563","https://openalex.org/W3005359536","https://openalex.org/W3009073662","https://openalex.org/W3009337595","https://openalex.org/W3009977275","https://openalex.org/W3034676907","https://openalex.org/W3035367622","https://openalex.org/W3081907075","https://openalex.org/W3094179451","https://openalex.org/W3096609285","https://openalex.org/W3101840387","https://openalex.org/W3108870912","https://openalex.org/W3116704196","https://openalex.org/W3119686997","https://openalex.org/W3121523901","https://openalex.org/W3123272955","https://openalex.org/W3124951096","https://openalex.org/W3126558081","https://openalex.org/W3128999341","https://openalex.org/W3139434170","https://openalex.org/W3151130473","https://openalex.org/W3154503495","https://openalex.org/W3168126494","https://openalex.org/W3168430381","https://openalex.org/W3170630188","https://openalex.org/W3175248300","https://openalex.org/W3177183540","https://openalex.org/W3178389175","https://openalex.org/W3182672186","https://openalex.org/W3204826552","https://openalex.org/W3206734547","https://openalex.org/W4299282685","https://openalex.org/W4304084267","https://openalex.org/W4309368547","https://openalex.org/W4385245566","https://openalex.org/W4387695008","https://openalex.org/W6638319203","https://openalex.org/W6755069125","https://openalex.org/W6784910987","https://openalex.org/W6787985011","https://openalex.org/W6796421146","https://openalex.org/W6797945588","https://openalex.org/W6798107787","https://openalex.org/W6798264847","https://openalex.org/W6798756522","https://openalex.org/W6802142178","https://openalex.org/W6810737600"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W4389116644","https://openalex.org/W2354198838","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W1989130879","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2103419012","https://openalex.org/W2952115151"],"abstract_inverted_index":{"Fine-grained":[0],"visual":[1],"classification":[2],"requires":[3],"distinguishing":[4],"sub-categories":[5],"within":[6,78,104],"the":[7,24,61,67,79,97,105,113,122,147,167],"same":[8],"super-category,":[9],"which":[10,31,56],"suffers":[11],"from":[12],"small":[13],"inter-class":[14,136],"and":[15,89,132,158],"large":[16],"intra-class":[17,129],"variances.":[18],"This":[19],"paper":[20],"aims":[21,94],"to":[22,48,59,95,112,127],"improve":[23],"FGVC":[25],"task":[26],"towards":[27],"better":[28],"performance,":[29],"for":[30,82],"we":[32,73,120],"deliver":[33],"a":[34,83],"novel":[35],"dual":[36],"Transformer":[37,80,106,117],"framework":[38],"(coined":[39],"Dual-TR)":[40],"with":[41,146],"multi-grained":[42,76],"assembly.":[43,91],"The":[44,92,108,161],"Dual-TR":[45,142],"is":[46,57],"well-designed":[47],"encode":[49],"fine-grained":[50],"objects":[51],"by":[52],"two":[53],"parallel":[54],"hierarchies,":[55],"amenable":[58],"capturing":[60],"subtle":[62],"yet":[63],"discriminative":[64],"cues":[65],"via":[66],"self-attention":[68,102],"mechanism":[69],"in":[70,100],"ViT.":[71],"Specifically,":[72],"perform":[74],"orthogonal":[75],"assembly":[77,115],"structure":[81],"more":[84],"robust":[85],"representation,":[86],"i.e.,":[87],"intra-layer":[88],"inter-layer":[90],"former":[93],"explore":[96],"informative":[98],"feature":[99],"various":[101],"heads":[103],"layer.":[107],"latter":[109],"pays":[110],"attention":[111],"token":[114],"across":[116],"layers.":[118],"Meanwhile,":[119],"introduce":[121],"constraint":[123],"of":[124,135,169],"center":[125],"loss":[126],"pull":[128],"samples\u2019":[130],"compactness":[131],"push":[133],"that":[134,141],"samples.":[137],"Extensive":[138],"experiments":[139],"show":[140],"performs":[143],"on":[144,150],"par":[145],"state-of-the-art":[148],"methods":[149],"four":[151],"public":[152],"benchmarks,":[153],"including":[154],"CUB-200-2011,":[155],"NABirds,":[156],"iNaturalist2017,":[157],"Stanford":[159],"Dogs.":[160],"comprehensive":[162],"ablation":[163],"studies":[164],"further":[165],"demonstrate":[166],"effectiveness":[168],"architectural":[170],"design":[171],"choices.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}