{"id":"https://openalex.org/W4385453669","doi":"https://doi.org/10.1109/tip.2023.3299495","title":"VTAE: Variational Transformer Autoencoder With Manifolds Learning","display_name":"VTAE: Variational Transformer Autoencoder With Manifolds Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385453669","doi":"https://doi.org/10.1109/tip.2023.3299495","pmid":"https://pubmed.ncbi.nlm.nih.gov/37527317"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3299495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3299495","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5079232252","display_name":"Pourya Shamsolmoali","orcid":"https://orcid.org/0000-0002-0263-1661"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Pourya Shamsolmoali","raw_affiliation_strings":["School of Communication and Electronic Engineering, East China Normal University, Shanghai, China","Queen's University Belfast, UK"],"affiliations":[{"raw_affiliation_string":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Queen's University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009550171","display_name":"Masoumeh Zareapoor","orcid":"https://orcid.org/0000-0002-3991-0584"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Masoumeh Zareapoor","raw_affiliation_strings":["School of Automation, Xi’an Jiao Tong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Xi’an Jiao Tong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066119228","display_name":"Huiyu Zhou","orcid":"https://orcid.org/0000-0003-1634-9840"},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huiyu Zhou","raw_affiliation_strings":["School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K"],"affiliations":[{"raw_affiliation_string":"School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K","institution_ids":["https://openalex.org/I153648349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["Faculty of Engineering, School of Computer Science, The University of Sydney, Darlington, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, School of Computer Science, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Key Laboratory of Intelligent Interaction and Applications, Ministry of Industry and Information Technology, and the School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Interaction and Applications, Ministry of Industry and Information Technology, and the School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I890469752","https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079232252"],"corresponding_institution_ids":["https://openalex.org/I126231945","https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":1.5647,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85292656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"4486","last_page":"4500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9995999932289124,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9995999932289124,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.992900013923645,"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/autoencoder","display_name":"Autoencoder","score":0.7154874801635742},{"id":"https://openalex.org/keywords/geodesic","display_name":"Geodesic","score":0.6626794338226318},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5203841924667358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5070900917053223},{"id":"https://openalex.org/keywords/riemannian-manifold","display_name":"Riemannian manifold","score":0.48532694578170776},{"id":"https://openalex.org/keywords/manifold-alignment","display_name":"Manifold alignment","score":0.4515678882598877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4482392370700836},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4411425292491913},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.4168597161769867},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.41367238759994507},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4114542603492737},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36256206035614014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3269227147102356},{"id":"https://openalex.org/keywords/nonlinear-dimensionality-reduction","display_name":"Nonlinear dimensionality reduction","score":0.31388458609580994},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.20747756958007812},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1768730878829956},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1023344099521637}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7154874801635742},{"id":"https://openalex.org/C165818556","wikidata":"https://www.wikidata.org/wiki/Q213488","display_name":"Geodesic","level":2,"score":0.6626794338226318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5203841924667358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5070900917053223},{"id":"https://openalex.org/C2779593128","wikidata":"https://www.wikidata.org/wiki/Q632814","display_name":"Riemannian manifold","level":2,"score":0.48532694578170776},{"id":"https://openalex.org/C153120616","wikidata":"https://www.wikidata.org/wiki/Q17068315","display_name":"Manifold alignment","level":4,"score":0.4515678882598877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4482392370700836},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4411425292491913},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.4168597161769867},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.41367238759994507},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4114542603492737},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36256206035614014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3269227147102356},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.31388458609580994},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.20747756958007812},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1768730878829956},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1023344099521637},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3299495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3299495","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37527317","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37527317","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 image processing : a publication of the IEEE Signal Processing Society","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":110,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1540288699","https://openalex.org/W1766336887","https://openalex.org/W1959608418","https://openalex.org/W2036996178","https://openalex.org/W2053186076","https://openalex.org/W2086920314","https://openalex.org/W2102166818","https://openalex.org/W2108501770","https://openalex.org/W2112796928","https://openalex.org/W2149466042","https://openalex.org/W2177899970","https://openalex.org/W2188365844","https://openalex.org/W2327562811","https://openalex.org/W2590796488","https://openalex.org/W2601564443","https://openalex.org/W2732026016","https://openalex.org/W2750384547","https://openalex.org/W2753738274","https://openalex.org/W2765340009","https://openalex.org/W2785519580","https://openalex.org/W2808508258","https://openalex.org/W2906083776","https://openalex.org/W2927928207","https://openalex.org/W2953421261","https://openalex.org/W2953952599","https://openalex.org/W2963373786","https://openalex.org/W2963703618","https://openalex.org/W2964082390","https://openalex.org/W2964127395","https://openalex.org/W2972632651","https://openalex.org/W2981352086","https://openalex.org/W3004988234","https://openalex.org/W3033617045","https://openalex.org/W3034543211","https://openalex.org/W3034671679","https://openalex.org/W3043547428","https://openalex.org/W3049651907","https://openalex.org/W3118608800","https://openalex.org/W3119469378","https://openalex.org/W3134430547","https://openalex.org/W3136958399","https://openalex.org/W3141862816","https://openalex.org/W3149124402","https://openalex.org/W3157073971","https://openalex.org/W3157152805","https://openalex.org/W3157286395","https://openalex.org/W3168773855","https://openalex.org/W3199003182","https://openalex.org/W3199920114","https://openalex.org/W3200296481","https://openalex.org/W3212924718","https://openalex.org/W4206441147","https://openalex.org/W4226400234","https://openalex.org/W4229081350","https://openalex.org/W4280607744","https://openalex.org/W4287324202","https://openalex.org/W4287588564","https://openalex.org/W4287645660","https://openalex.org/W4287765638","https://openalex.org/W4287816707","https://openalex.org/W4287864501","https://openalex.org/W4288333413","https://openalex.org/W4288356932","https://openalex.org/W4294170691","https://openalex.org/W4296562951","https://openalex.org/W4297688279","https://openalex.org/W4297847622","https://openalex.org/W4298392613","https://openalex.org/W4312290517","https://openalex.org/W4312291121","https://openalex.org/W4312567873","https://openalex.org/W4312771828","https://openalex.org/W4312947743","https://openalex.org/W4320013936","https://openalex.org/W6618372016","https://openalex.org/W6637994300","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6681637710","https://openalex.org/W6682691769","https://openalex.org/W6687045409","https://openalex.org/W6694954494","https://openalex.org/W6702162793","https://openalex.org/W6718379498","https://openalex.org/W6733793881","https://openalex.org/W6743446608","https://openalex.org/W6743688258","https://openalex.org/W6744627333","https://openalex.org/W6745712377","https://openalex.org/W6745907911","https://openalex.org/W6748223763","https://openalex.org/W6748391871","https://openalex.org/W6749101112","https://openalex.org/W6752767679","https://openalex.org/W6760514122","https://openalex.org/W6762655333","https://openalex.org/W6773937809","https://openalex.org/W6773968902","https://openalex.org/W6774295056","https://openalex.org/W6774448971","https://openalex.org/W6779908401","https://openalex.org/W6783731041","https://openalex.org/W6788231789","https://openalex.org/W6792203520","https://openalex.org/W6794315554","https://openalex.org/W6796458225","https://openalex.org/W6796695178","https://openalex.org/W6811154502","https://openalex.org/W6843428480"],"related_works":["https://openalex.org/W2355395139","https://openalex.org/W2988134182","https://openalex.org/W3109610583","https://openalex.org/W2387045723","https://openalex.org/W2375518579","https://openalex.org/W117517268","https://openalex.org/W2944373987","https://openalex.org/W65619410","https://openalex.org/W2112684860","https://openalex.org/W4387713464"],"abstract_inverted_index":{"Deep":[0],"generative":[1,96],"models":[2,20,174],"have":[3,151],"demonstrated":[4],"successful":[5],"applications":[6],"in":[7,58],"learning":[8],"non-linear":[9,23],"data":[10,32,54,83,139],"distributions":[11],"through":[12],"a":[13,22,70,101,112,141,166,197],"number":[14],"of":[15,40,52,94,199],"latent":[16,28,46,135,162],"variables":[17],"and":[18,73,79,115,144,153,194,206],"these":[19],"use":[21,176],"function":[24],"(generator)":[25],"to":[26,108,131,138,150],"map":[27],"samples":[29,84],"into":[30],"the":[31,35,38,41,45,53,86,92,124,134,172],"space.":[33],"On":[34],"other":[36],"hand,":[37],"non-linearity":[39],"generator":[42],"implies":[43],"that":[44,76,175,186],"space":[47],"shows":[48],"an":[49,128],"unsatisfactory":[50],"projection":[51],"space,":[55],"which":[56],"results":[57],"poor":[59],"representation":[60,117],"learning.":[61,118],"This":[62],"weak":[63],"projection,":[64],"however,":[65],"can":[66,89,190],"be":[67],"addressed":[68],"by":[69],"Riemannian":[71,87,113,142],"metric,":[72],"we":[74,121,164],"show":[75,185],"geodesics":[77,110],"computation":[78],"accurate":[80],"interpolations":[81,155],"between":[82,158],"on":[85,111,140,183],"manifold":[88,114],"substantially":[90],"improve":[91,116,191],"performance":[93],"deep":[95],"models.":[97],"In":[98,119],"this":[99],"paper,":[100],"Variational":[102],"spatial-Transformer":[103,130],"AutoEncoder":[104],"(VTAE)":[105],"is":[106],"proposed":[107,188],"minimize":[109],"particular,":[120],"carefully":[122],"design":[123],"variational":[125],"autoencoder":[126],"with":[127,179],"encoded":[129],"explicitly":[132],"expand":[133],"variable":[136],"model":[137,189],"manifold,":[143],"obtain":[145],"global":[146],"context":[147],"modelling.":[148],"Moreover,":[149],"smooth":[152],"plausible":[154],"while":[156],"traversing":[157],"two":[159],"different":[160,170],"objects'":[161],"representations,":[163],"propose":[165],"geodesic":[167],"interpolation":[168,178],"network":[169],"from":[171],"existing":[173],"linear":[177],"inferior":[180],"performance.":[181],"Experiments":[182],"benchmarks":[184],"our":[187],"predictive":[192],"accuracy":[193],"versatility":[195],"over":[196],"range":[198],"computer":[200],"vision":[201],"tasks,":[202],"including":[203],"image":[204],"interpolations,":[205],"reconstructions.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}