{"id":"https://openalex.org/W4416252050","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227769","title":"HSViT: Horizontally Scalable Vision Transformer","display_name":"HSViT: Horizontally Scalable Vision Transformer","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252050","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227769"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5011685108","display_name":"Chenhao Xu","orcid":"https://orcid.org/0000-0003-0819-7269"},"institutions":[{"id":"https://openalex.org/I71270174","display_name":"Victoria University","ror":"https://ror.org/04j757h98","country_code":"AU","type":"education","lineage":["https://openalex.org/I71270174"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Chenhao Xu","raw_affiliation_strings":["Victoria University,ISILC,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Victoria University,ISILC,Melbourne,Australia","institution_ids":["https://openalex.org/I71270174"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075200053","display_name":"Chang\u2010Tsun Li","orcid":"https://orcid.org/0000-0003-4735-6138"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chang-Tsun Li","raw_affiliation_strings":["Deakin University,School of IT,Geelong,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University,School of IT,Geelong,Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072923302","display_name":"Chee Peng Lim","orcid":"https://orcid.org/0000-0003-4191-9083"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chee Peng Lim","raw_affiliation_strings":["Swinburne University of Technology,Department of Computing Technologies,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology,Department of Computing Technologies,Melbourne,Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046519614","display_name":"Douglas Creighton","orcid":"https://orcid.org/0000-0002-9217-1231"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Douglas Creighton","raw_affiliation_strings":["Deakin University,IISRI,Geelong,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University,IISRI,Geelong,Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011685108"],"corresponding_institution_ids":["https://openalex.org/I71270174"],"apc_list":null,"apc_paid":null,"fwci":0.9662,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81642942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.60589998960495,"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":0.60589998960495,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.04659999907016754,"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"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.03269999846816063,"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/scalability","display_name":"Scalability","score":0.7017999887466431},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6912999749183655},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6832000017166138},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5322999954223633},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5234000086784363},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"Inductive bias","score":0.33739998936653137},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.33009999990463257}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7017999887466431},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6912999749183655},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6832000017166138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6306999921798706},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.33739998936653137},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2963163009","https://openalex.org/W2991040477","https://openalex.org/W3012125688","https://openalex.org/W3034421924","https://openalex.org/W3035617116","https://openalex.org/W3047357290","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3166384310","https://openalex.org/W3203701986","https://openalex.org/W4214493665","https://openalex.org/W4226224676","https://openalex.org/W4312349930","https://openalex.org/W4312885563","https://openalex.org/W4312950730","https://openalex.org/W4313002018","https://openalex.org/W4385245566","https://openalex.org/W4386076539","https://openalex.org/W4387353472","https://openalex.org/W4390872447","https://openalex.org/W4390872693","https://openalex.org/W4393373882","https://openalex.org/W4400410870"],"related_works":[],"abstract_inverted_index":{"While":[0],"the":[1,36,89,99,104,157],"Vision":[2,70],"Transformer":[3,71,90],"(ViT)":[4],"architecture":[5,120],"gains":[6],"prominence":[7],"in":[8,15,42,51],"computer":[9],"vision":[10],"and":[11,27,39,127],"finds":[12],"growing":[13],"applications":[14],"edge":[16,52,131],"computing,":[17],"its":[18],"lack":[19],"of":[20,160],"strong":[21,110],"inductive":[22,96],"biases":[23],"regarding":[24],"shift,":[25],"scale,":[26],"rotational":[28],"invariance":[29],"necessitates":[30],"pre-training":[31,107],"on":[32,112,151,168],"large-scale":[33],"datasets.":[34,114],"Moreover,":[35],"increasing":[37],"depth":[38],"parameter":[40],"counts":[41],"ViT":[43],"models":[44],"present":[45],"significant":[46],"challenges":[47],"for":[48,106],"training,":[49],"particularly":[50],"environments":[53],"where":[54],"computational":[55],"resources":[56],"are":[57],"constrained.":[58],"To":[59],"mitigate":[60],"these":[61],"challenges,":[62],"this":[63],"paper":[64],"introduces":[65],"a":[66,75,116],"novel":[67,76,117],"Horizontally":[68],"Scalable":[69],"(HSViT)":[72],"architecture.":[73],"Specifically,":[74],"image-level":[77],"feature":[78],"embedding":[79],"approach":[80],"is":[81,121,172],"introduced":[82],"that":[83],"incorporates":[84],"convolutional":[85],"layers":[86],"prior":[87],"to":[88,101,143,166],"blocks.":[91],"This":[92],"design":[93],"helps":[94],"preserve":[95],"biases,":[97],"allowing":[98],"model":[100,125],"potentially":[102],"eliminate":[103],"need":[105],"while":[108,155],"achieving":[109],"performance":[111],"small":[113,153],"Furthermore,":[115],"horizontally":[118],"scalable":[119],"designed,":[122],"facilitating":[123],"collaborative":[124],"training":[126],"inference":[128],"across":[129],"multiple":[130],"devices.":[132],"The":[133,170],"experimental":[134],"results":[135],"show":[136],"that,":[137],"without":[138],"pre-training,":[139],"HSViT":[140],"achieves":[141],"up":[142,165],"10%":[144],"higher":[145],"top-1":[146,158],"accuracy":[147,159],"than":[148],"state-of-the-art":[149],"methods":[150],"several":[152],"datasets,":[154],"improving":[156],"existing":[161],"CNN":[162],"backbones":[163],"by":[164],"3.1%":[167],"ImageNet-1k.":[169],"code":[171],"available":[173],"at":[174],"https://github.com/xuchenhao001/HSViT.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-03T09:05:47.796612","created_date":"2025-11-14T00:00:00"}