{"id":"https://openalex.org/W4387331367","doi":"https://doi.org/10.1109/tpami.2023.3306164","title":"Guest Editorial Introduction to the Special Section on Transformer Models in Vision","display_name":"Guest Editorial Introduction to the Special Section on Transformer Models in Vision","publication_year":2023,"publication_date":"2023-10-04","ids":{"openalex":"https://openalex.org/W4387331367","doi":"https://doi.org/10.1109/tpami.2023.3306164"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3306164","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3306164","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/10269680/10269654.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"editorial","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/34/10269680/10269654.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000300751","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-9502-1749"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","AU"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","Australian National University, Canberra, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9502-1749","affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103024730","display_name":"Ashish Vaswani","orcid":"https://orcid.org/0000-0002-7794-2085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Vaswani","raw_affiliation_strings":["Stealth, Mountain View, WY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stealth, Mountain View, WY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005777963","display_name":"Niki Parmar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niki Parmar","raw_affiliation_strings":["Stealth, Mountain View, WY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stealth, Mountain View, WY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418319","display_name":"Ming\u2013Hsuan Yang","orcid":"https://orcid.org/0000-0003-4848-2304"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Hsuan Yang","raw_affiliation_strings":["University of California, Merced, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080823547","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0001-6172-5572"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"11","first_page":"12721","last_page":"12725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8912000060081482,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8912000060081482,"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/T10028","display_name":"Topic Modeling","score":0.8580999970436096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7549772262573242},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7119961977005005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.631925106048584},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6019014120101929},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5312851071357727},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.511116087436676},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4758151173591614},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.46333399415016174},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42875537276268005},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4122304320335388},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35082656145095825},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33223870396614075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2898402512073517},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2689273953437805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12207955121994019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549772262573242},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7119961977005005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.631925106048584},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6019014120101929},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5312851071357727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.511116087436676},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4758151173591614},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.46333399415016174},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42875537276268005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4122304320335388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35082656145095825},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33223870396614075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2898402512073517},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2689273953437805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12207955121994019},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpami.2023.3306164","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3306164","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/10269680/10269654.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tpami.2023.3306164","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3306164","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/10269680/10269654.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387331367.pdf","grobid_xml":"https://content.openalex.org/works/W4387331367.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W4283023197","https://openalex.org/W4289535682","https://openalex.org/W4292347911","https://openalex.org/W4292973282","https://openalex.org/W4293680532","https://openalex.org/W4294811378","https://openalex.org/W4295903508","https://openalex.org/W4297095249","https://openalex.org/W4304479854","https://openalex.org/W4307092789","https://openalex.org/W4312313760","https://openalex.org/W4312988544","https://openalex.org/W4313123992","https://openalex.org/W4313427331","https://openalex.org/W4319777850","https://openalex.org/W4319777935","https://openalex.org/W4319878275","https://openalex.org/W4328007221"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W4381058564","https://openalex.org/W2903533908","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W2903399267","https://openalex.org/W2949454572"],"abstract_inverted_index":{"Transformer":[0,70],"models":[1,43,71],"have":[2,75],"achieved":[3],"outstanding":[4],"results":[5],"on":[6],"a":[7,54,68],"variety":[8],"of":[9,27],"language":[10],"tasks,":[11],"such":[12],"as":[13],"text":[14],"classification,":[15],"ma-":[16],"chine":[17],"translation,":[18],"and":[19,46,64,72,95],"question":[20,97],"answering.":[21],"This":[22],"success":[23],"in":[24,35],"the":[25,36,58],"field":[26],"Natural":[28],"Language":[29],"Processing":[30],"(NLP)":[31],"has":[32,53],"sparked":[33],"interest":[34],"computer":[37],"vision":[38,45],"community":[39],"to":[40,44,60],"apply":[41],"these":[42],"multi-modal":[47],"learning":[48],"tasks.":[49],"However,":[50],"visual":[51,96],"data":[52],"unique":[55],"structure,":[56],"requiring":[57],"need":[59],"rethink":[61],"network":[62],"designs":[63],"training":[65],"methods.":[66],"As":[67],"result,":[69],"their":[73],"variations":[74],"been":[76],"suc-":[77],"cessfully":[78],"used":[79],"for":[80],"image":[81,87,91],"recognition,":[82],"object":[83],"detection,":[84],"seg-":[85],"mentation,":[86],"super-resolution,":[88],"video":[89],"understanding,":[90],"generation,":[92],"text-image":[93],"synthesis,":[94],"answering,":[98],"among":[99],"other":[100],"applications.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
