{"id":"https://openalex.org/W4366352791","doi":"https://doi.org/10.1109/tpami.2023.3268446","title":"Dual Vision Transformer","display_name":"Dual Vision Transformer","publication_year":2023,"publication_date":"2023-04-19","ids":{"openalex":"https://openalex.org/W4366352791","doi":"https://doi.org/10.1109/tpami.2023.3268446","pmid":"https://pubmed.ncbi.nlm.nih.gov/37074902"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3268446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3268446","pdf_url":null,"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":"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/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7587-101X","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041154840","display_name":"Yehao Li","orcid":"https://orcid.org/0000-0002-9603-1113"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yehao Li","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9603-1113","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085403640","display_name":"Yingwei Pan","orcid":"https://orcid.org/0000-0002-4344-8898"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingwei Pan","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4344-8898","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445377","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-4219-781X"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4219-781X","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363146","display_name":"Xiao\u2013Ping Zhang","orcid":"https://orcid.org/0000-0001-5241-0069"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiao-Ping Zhang","raw_affiliation_strings":["Ryerson University, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5241-0069","affiliations":[{"raw_affiliation_string":"Ryerson University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I530967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2497-7732","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5088760097"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.446,"has_fulltext":false,"cited_by_count":154,"citation_normalized_percentile":{"value":0.99539861,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"45","issue":"9","first_page":"10870","last_page":"10882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997000098228455,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7663358449935913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5828038454055786},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5669232606887817},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5134361982345581},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.49255260825157166},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4620057940483093},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4415455460548401},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42718833684921265},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42701026797294617},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32793793082237244},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2263297438621521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663358449935913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5828038454055786},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5669232606887817},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5134361982345581},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.49255260825157166},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4620057940483093},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4415455460548401},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42718833684921265},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42701026797294617},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32793793082237244},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2263297438621521},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3268446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3268446","pdf_url":null,"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"},{"id":"pmid:37074902","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37074902","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2507296351","https://openalex.org/W2549139847","https://openalex.org/W2806070179","https://openalex.org/W2884822772","https://openalex.org/W2908510526","https://openalex.org/W2910628332","https://openalex.org/W2922509574","https://openalex.org/W2928165649","https://openalex.org/W2949391068","https://openalex.org/W2953937638","https://openalex.org/W2955425717","https://openalex.org/W2963263347","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2964309882","https://openalex.org/W2983446232","https://openalex.org/W2998508940","https://openalex.org/W3014641072","https://openalex.org/W3034885317","https://openalex.org/W3035253074","https://openalex.org/W3035284526","https://openalex.org/W3035396860","https://openalex.org/W3035682985","https://openalex.org/W3094502228","https://openalex.org/W3102710196","https://openalex.org/W3117876421","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3137278571","https://openalex.org/W3137963805","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3157528469","https://openalex.org/W3166942762","https://openalex.org/W3170874841","https://openalex.org/W3172509117","https://openalex.org/W3172752666","https://openalex.org/W3172801447","https://openalex.org/W3175515048","https://openalex.org/W3176153963","https://openalex.org/W3183430956","https://openalex.org/W4213019189","https://openalex.org/W4214493665","https://openalex.org/W4214614183","https://openalex.org/W4214634256","https://openalex.org/W4214636423","https://openalex.org/W4282964635","https://openalex.org/W4282968790","https://openalex.org/W4283023197","https://openalex.org/W4295308583","https://openalex.org/W4297665946","https://openalex.org/W4298395628","https://openalex.org/W4312800447","https://openalex.org/W4312832682","https://openalex.org/W4312950730","https://openalex.org/W4313125078","https://openalex.org/W4313170858","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6684191040","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6748481559","https://openalex.org/W6753421600","https://openalex.org/W6757817989","https://openalex.org/W6762718338","https://openalex.org/W6763367864","https://openalex.org/W6764990469","https://openalex.org/W6775845032","https://openalex.org/W6779586474","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6791705549","https://openalex.org/W6794345597","https://openalex.org/W6796526935","https://openalex.org/W6796721132","https://openalex.org/W6797153837","https://openalex.org/W6797533734","https://openalex.org/W6798016242","https://openalex.org/W6798046796","https://openalex.org/W6802968523"],"related_works":["https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297","https://openalex.org/W4280645561"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"have":[2],"presented":[3],"several":[4],"strategies":[5],"to":[6,60,163,168],"mitigate":[7],"the":[8,22,50,63,78,148,157],"computations":[9],"of":[10,17,110,156],"self-attention":[11,24,82,150,170],"mechanism":[12],"with":[13,107,189],"high-resolution":[14],"inputs.":[15],"Many":[16],"these":[18,46],"works":[19],"consider":[20],"decomposing":[21],"global":[23,64,79,105,114,166],"procedure":[25],"over":[26],"image":[27],"patches":[28],"into":[29,104],"regional":[30],"and":[31,56,137,143],"local":[32,125],"feature":[33],"extraction":[34],"procedures":[35],"that":[36,75,97,180],"each":[37],"incurs":[38],"a":[39,71,93],"smaller":[40],"computational":[41,175],"complexity.":[42,111,176,192],"Despite":[43],"good":[44],"efficiency,":[45],"approaches":[47],"seldom":[48],"explore":[49],"holistic":[51],"interactions":[52],"among":[53],"all":[54],"patches,":[55],"are":[57,140,144],"thus":[58],"difficult":[59],"fully":[61],"capture":[62],"semantics.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"novel":[72],"Transformer":[73,87,187],"architecture":[74,91],"elegantly":[76],"exploits":[77],"semantics":[80,106,115,167],"for":[81],"learning,":[83],"namely":[84],"Dual":[85],"Vision":[86],"(Dual-ViT).":[88],"The":[89,134],"new":[90],"incorporates":[92],"critical":[94],"semantic":[95,135],"pathway":[96,136,139],"can":[98],"more":[99],"efficiently":[100],"compress":[101],"token":[102],"vectors":[103],"reduced":[108],"order":[109],"Such":[112],"compressed":[113],"then":[116],"serve":[117],"as":[118],"useful":[119],"prior":[120],"information":[121,151],"in":[122,152],"learning":[123,171],"finer":[124],"pixel":[126,132,138],"level":[127],"details,":[128],"through":[129,154],"another":[130],"constructed":[131],"pathway.":[133],"integrated":[141],"together":[142],"jointly":[145],"trained,":[146],"spreading":[147],"enhanced":[149],"parallel":[153],"both":[155],"pathways.":[158],"Dual-ViT":[159,181],"is":[160],"henceforth":[161],"able":[162],"capitalize":[164],"on":[165],"boost":[169],"without":[172],"compromising":[173],"much":[174],"We":[177],"empirically":[178],"demonstrate":[179],"provides":[182],"superior":[183],"accuracy":[184],"than":[185],"SOTA":[186],"architectures":[188],"comparable":[190],"training":[191]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}