{"id":"https://openalex.org/W4380032284","doi":"https://doi.org/10.1109/tcsvt.2023.3284812","title":"DATran: Dual Attention Transformer for Multi-Label Image Classification","display_name":"DATran: Dual Attention Transformer for Multi-Label Image Classification","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4380032284","doi":"https://doi.org/10.1109/tcsvt.2023.3284812"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3284812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3284812","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/A5059433400","display_name":"Wei Zhou","orcid":"https://orcid.org/0000-0002-9237-7205"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9237-7205","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068707953","display_name":"Zhijie Zheng","orcid":"https://orcid.org/0000-0002-5584-1785"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Zheng","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5584-1785","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001383559","display_name":"Tao Su","orcid":"https://orcid.org/0000-0001-5227-1337"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Su","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5227-1337","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056953478","display_name":"Haifeng Hu","orcid":"https://orcid.org/0000-0002-4884-323X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Hu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4884-323X","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":3.5487,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94097884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"34","issue":"1","first_page":"342","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9965000152587891,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.7858265042304993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6337483525276184},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6239138841629028},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5629777312278748},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5627538561820984},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.4385245442390442},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43546047806739807},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4166225790977478},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.41203078627586365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3311009705066681},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25719714164733887},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.12279412150382996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858265042304993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6337483525276184},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6239138841629028},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5629777312278748},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5627538561820984},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4385245442390442},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43546047806739807},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4166225790977478},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.41203078627586365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3311009705066681},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25719714164733887},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.12279412150382996},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/tcsvt.2023.3284812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3284812","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":[],"awards":[{"id":"https://openalex.org/G5355820501","display_name":"\u4eba\u8138\u56fe\u50cf\u7279\u5f81\u62bd\u53d6\u53ca\u5206\u7c7b\u5668\u8bbe\u8ba1\u82e5\u5e72\u95ee\u9898\u7814\u7a76","funder_award_id":"60802069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5678804896","display_name":null,"funder_award_id":"61673402","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G709867051","display_name":null,"funder_award_id":"61273270","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8307738215","display_name":null,"funder_award_id":"62076262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W1567302070","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1998660429","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2109255472","https://openalex.org/W2166912588","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2410641892","https://openalex.org/W2560023338","https://openalex.org/W2560096627","https://openalex.org/W2562379650","https://openalex.org/W2565639579","https://openalex.org/W2752782242","https://openalex.org/W2808496655","https://openalex.org/W2809273606","https://openalex.org/W2921251850","https://openalex.org/W2932399282","https://openalex.org/W2955058313","https://openalex.org/W2957702778","https://openalex.org/W2962858109","https://openalex.org/W2963020325","https://openalex.org/W2963091558","https://openalex.org/W2963300078","https://openalex.org/W2963322224","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2964015378","https://openalex.org/W2964231884","https://openalex.org/W2976845662","https://openalex.org/W2981689412","https://openalex.org/W2982112268","https://openalex.org/W2982220924","https://openalex.org/W2999565440","https://openalex.org/W3005396940","https://openalex.org/W3034552520","https://openalex.org/W3034580371","https://openalex.org/W3034655362","https://openalex.org/W3034924978","https://openalex.org/W3035666869","https://openalex.org/W3087020912","https://openalex.org/W3088493063","https://openalex.org/W3089555680","https://openalex.org/W3092483887","https://openalex.org/W3092779813","https://openalex.org/W3093484105","https://openalex.org/W3095907242","https://openalex.org/W3109067582","https://openalex.org/W3112165001","https://openalex.org/W3120129399","https://openalex.org/W3138516171","https://openalex.org/W3165181705","https://openalex.org/W3166394261","https://openalex.org/W3167456680","https://openalex.org/W3174396085","https://openalex.org/W3176136157","https://openalex.org/W3176443126","https://openalex.org/W3183768965","https://openalex.org/W3184087575","https://openalex.org/W3189532445","https://openalex.org/W3192931333","https://openalex.org/W3202884348","https://openalex.org/W3205618423","https://openalex.org/W3211407538","https://openalex.org/W3216083537","https://openalex.org/W4207054665","https://openalex.org/W4220821435","https://openalex.org/W4221079634","https://openalex.org/W4226467581","https://openalex.org/W4285186657","https://openalex.org/W4286499389","https://openalex.org/W4289752563","https://openalex.org/W4295788787","https://openalex.org/W4304084267","https://openalex.org/W4312289196","https://openalex.org/W4312938052","https://openalex.org/W4385245566","https://openalex.org/W6726873649","https://openalex.org/W6754416387","https://openalex.org/W6763367864","https://openalex.org/W6767960695","https://openalex.org/W6788601362","https://openalex.org/W6796617330","https://openalex.org/W6798617289","https://openalex.org/W7047843660"],"related_works":["https://openalex.org/W2911497689","https://openalex.org/W2952813363","https://openalex.org/W4360783045","https://openalex.org/W2963346891","https://openalex.org/W3176438653","https://openalex.org/W2770149305","https://openalex.org/W3167930666","https://openalex.org/W3014952856","https://openalex.org/W3010730661","https://openalex.org/W3217780232"],"abstract_inverted_index":{"Multi-label":[0],"image":[1,106],"classification":[2,84],"is":[3,238],"a":[4,17,124,133,164,188,215],"fundamental":[5],"yet":[6],"challenging":[7],"task,":[8],"which":[9,131],"aims":[10],"to":[11,47,57,61,76,149,158,171,194,207,221,252,268],"predict":[12],"the":[13,26,30,48,67,72,78,83,100,113,151,196,209,223,232,255,259,270],"labels":[14,104],"associated":[15],"with":[16],"given":[18],"image.":[19],"Most":[20],"of":[21,33,51,116,261],"previous":[22],"methods":[23,41,90,155],"directly":[24],"exploit":[25,71],"high-level":[27,180],"features":[28,45,60,272],"from":[29,143,201],"last":[31],"layer":[32],"convolutional":[34,52],"neural":[35],"network":[36,75],"for":[37,81,273],"classification.":[38,274],"However,":[39],"these":[40,89,262],"cannot":[42],"obtain":[43,269],"global":[44],"due":[46],"limited":[49],"size":[50],"kernels,":[53],"and":[54,105,108,140,182,244,248,286],"they":[55,98],"fail":[56],"extract":[58],"multi-scale":[59,166,173],"effectively":[62,230],"recognize":[63,159],"small-scale":[64],"objects":[65,200],"in":[66,147,205],"images.":[68,117,145],"Recent":[69],"studies":[70],"graph":[73,95],"convolution":[74],"model":[77,210,292],"label":[79],"correlations":[80,142],"boosting":[82],"performance.":[85,211],"Despite":[86],"substantial":[87],"progress,":[88],"rely":[91],"on":[92,280],"manually":[93],"pre-defined":[94],"structures.":[96],"Besides,":[97],"ignore":[99],"associations":[101],"between":[102,199,225,234],"semantic":[103,235],"regions,":[107],"do":[109],"not":[110],"fully":[111],"explore":[112],"spatial":[114,139,190,203],"context":[115],"To":[118],"address":[119],"above":[120],"issues,":[121],"we":[122,162,186,213],"propose":[123],"novel":[125],"Dual":[126],"Attention":[127],"Transformer":[128],"(DATran)":[129],"model,":[130],"adopts":[132],"dual-stream":[134],"architecture":[135],"that":[136,153,241,290],"simultaneously":[137],"learns":[138],"channel":[141,217,227],"multi-label":[144],"Firstly,":[146],"order":[148],"solve":[150],"problem":[152],"current":[154,297],"are":[156,266,278],"difficult":[157],"small-size":[160],"objects,":[161],"develop":[163],"new":[165],"feature":[167,174,256],"fusion":[168],"(MSFF)":[169],"module":[170,193,220,243,246],"generate":[172],"representation":[175],"by":[176],"jointly":[177],"integrating":[178],"both":[179],"semantics":[181],"low-level":[183],"details.":[184],"Secondly,":[185],"design":[187],"prior-enhanced":[189,216],"attention":[191,218,264],"(PSA)":[192],"learn":[195],"long-range":[197],"correlation":[198,233],"different":[202,226],"positions":[204],"images":[206],"enhance":[208],"Thirdly,":[212],"devise":[214],"(PCA)":[219],"capture":[222],"inter-dependencies":[224],"maps,":[228],"thus":[229],"improving":[231],"categories.":[236],"It":[237],"worth":[239],"noting":[240],"PSA":[242],"PCA":[245],"complement":[247],"promote":[249],"each":[250],"other":[251],"further":[253],"augment":[254],"representations.":[257],"Finally,":[258],"outputs":[260],"two":[263],"modules":[265],"fused":[267],"final":[271],"Performance":[275],"evaluation":[276],"experiments":[277],"conducted":[279],"MS-COCO":[281],"2014,":[282],"PASCAL":[283],"VOC":[284],"2007":[285],"VG-500":[287],"datasets,":[288],"demonstrating":[289],"DATran":[291],"achieves":[293],"better":[294],"performance":[295],"than":[296],"state-of-the-art":[298],"models.":[299]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}