{"id":"https://openalex.org/W4313887039","doi":"https://doi.org/10.1109/tnnls.2023.3234166","title":"End-to-End Multitask Learning With Vision Transformer","display_name":"End-to-End Multitask Learning With Vision Transformer","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4313887039","doi":"https://doi.org/10.1109/tnnls.2023.3234166","pmid":"https://pubmed.ncbi.nlm.nih.gov/37018576"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3234166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3234166","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5032861309","display_name":"Yingjie Tian","orcid":"https://orcid.org/0000-0002-4675-0398"},"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/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":"Yingjie Tian","raw_affiliation_strings":["School of Economics and Management, University of Chinese Academy of Sciences, Beijing, China","Research Center on Fictitious Economy and Data Science, and the Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4675-0398","affiliations":[{"raw_affiliation_string":"School of Economics and Management, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Research Center on Fictitious Economy and Data Science, and the Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091532986","display_name":"Kunlong Bai","orcid":"https://orcid.org/0000-0002-8897-746X"},"institutions":[{"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":"Kunlong Bai","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8897-746X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032861309"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.7265,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91792011,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"35","issue":"7","first_page":"9579","last_page":"9590"},"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":0.9965999722480774,"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":0.9965999722480774,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9947999715805054,"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/multi-task-learning","display_name":"Multi-task learning","score":0.8244317173957825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7918292284011841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6303574442863464},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6161611080169678},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5770817995071411},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5768939852714539},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44357478618621826},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4423518180847168},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4149984121322632},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3473079204559326}],"concepts":[{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.8244317173957825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918292284011841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6303574442863464},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6161611080169678},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5770817995071411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5768939852714539},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44357478618621826},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4423518180847168},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4149984121322632},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3473079204559326},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3234166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3234166","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37018576","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37018576","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G3913342317","display_name":null,"funder_award_id":"12071458","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7426924815","display_name":null,"funder_award_id":"71731009","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W4301248618","https://openalex.org/W2165343651","https://openalex.org/W2242427765","https://openalex.org/W2075830955","https://openalex.org/W2343790552","https://openalex.org/W3111398917","https://openalex.org/W4385507578","https://openalex.org/W2949157572"],"abstract_inverted_index":{"Multitask":[0],"learning":[1,70],"(MTL)":[2],"is":[3,47,112,175,183,208],"a":[4,67,78,105,115,201],"challenging":[5],"puzzle,":[6],"particularly":[7],"in":[8,90,204],"the":[9,34,42,58,85,99,136,141,215],"realm":[10],"of":[11,44,61,140],"computer":[12],"vision":[13,62],"(CV).":[14],"Setting":[15],"up":[16],"vanilla":[17],"deep":[18],"MTL":[19,45,192],"requires":[20,144],"either":[21],"hard":[22],"or":[23,182],"soft":[24],"parameter":[25],"sharing":[26],"schemes":[27],"that":[28,92,177,214],"employ":[29],"greedy":[30],"search":[31],"to":[32,49,65,82,126,200],"find":[33],"optimal":[35],"network":[36,190],"designs.":[37],"Despite":[38],"its":[39],"widespread":[40],"application,":[41],"performance":[43,219],"models":[46],"vulnerable":[48],"under-constrained":[50],"parameters.":[51],"In":[52,124,194],"this":[53],"article,":[54],"we":[55,196],"draw":[56],"on":[57,148,162,184],"recent":[59],"success":[60],"transformer":[63,81],"(ViT)":[64],"propose":[66],"multitask":[68,73],"representation":[69],"method":[71,131,199],"called":[72],"ViT":[74,142],"(MTViT),":[75],"which":[76,173,205],"proposes":[77],"multiple":[79],"branch":[80,111],"sequentially":[83],"process":[84],"image":[86],"patches":[87],"(i.e.,":[88],"tokens":[89],"transformer)":[91],"are":[93,159,222],"associated":[94],"with":[95,120,186],"various":[96],"tasks.":[97],"Through":[98],"proposed":[100,130,179],"cross-task":[101],"attention":[102],"(CA)":[103],"module,":[104],"task":[106,110,122,206],"token":[107],"from":[108],"each":[109],"regarded":[113],"as":[114],"query":[116],"for":[117],"exchanging":[118],"information":[119],"other":[121],"branches.":[123],"contrast":[125],"prior":[127],"models,":[128],"our":[129,178,198],"extracts":[132],"intrinsic":[133],"features":[134],"using":[135],"built-in":[137],"self-attention":[138],"mechanism":[139],"and":[143,150,170],"just":[145],"linear":[146],"time":[147],"memory":[149],"computation":[151],"complexity,":[152],"rather":[153],"than":[154],"quadratic":[155],"time.":[156],"Comprehensive":[157],"experiments":[158],"carried":[160],"out":[161],"two":[163],"benchmark":[164],"datasets,":[165],"including":[166],"NYU-Depth":[167],"V2":[168],"(NYUDv2)":[169],"CityScapes,":[171],"after":[172],"it":[174],"found":[176],"MTViT":[180,216],"outperforms":[181],"par":[185],"existing":[187],"convolutional":[188],"neural":[189],"(CNN)-based":[191],"methods.":[193],"addition,":[195],"apply":[197],"synthetic":[202],"dataset":[203],"relatedness":[207],"controlled.":[209],"Surprisingly,":[210],"experimental":[211],"results":[212],"reveal":[213],"exhibits":[217],"excellent":[218],"when":[220],"tasks":[221],"less":[223],"related.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}