{"id":"https://openalex.org/W4372267514","doi":"https://doi.org/10.1109/icassp49357.2023.10096453","title":"GSWIN: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","display_name":"GSWIN: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267514","doi":"https://doi.org/10.1109/icassp49357.2023.10096453"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5045898102","display_name":"Mocho Go","orcid":null},"institutions":[{"id":"https://openalex.org/I148798404","display_name":"Tokyo University of Technology","ror":"https://ror.org/021a26605","country_code":"JP","type":"education","lineage":["https://openalex.org/I148798404"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mocho Go","raw_affiliation_strings":["PKSHA Technology, Inc.,Tokyo,Japan","PKSHA Technology, Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"PKSHA Technology, Inc.,Tokyo,Japan","institution_ids":["https://openalex.org/I148798404"]},{"raw_affiliation_string":"PKSHA Technology, Inc., Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039623511","display_name":"H. Tachibana","orcid":"https://orcid.org/0000-0001-5162-1294"},"institutions":[{"id":"https://openalex.org/I148798404","display_name":"Tokyo University of Technology","ror":"https://ror.org/021a26605","country_code":"JP","type":"education","lineage":["https://openalex.org/I148798404"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideyuki Tachibana","raw_affiliation_strings":["PKSHA Technology, Inc.,Tokyo,Japan","PKSHA Technology, Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"PKSHA Technology, Inc.,Tokyo,Japan","institution_ids":["https://openalex.org/I148798404"]},{"raw_affiliation_string":"PKSHA Technology, Inc., Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045898102"],"corresponding_institution_ids":["https://openalex.org/I148798404"],"apc_list":null,"apc_paid":null,"fwci":0.9803,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77928358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9970999956130981,"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/T10320","display_name":"Neural Networks and Applications","score":0.9970999956130981,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9950000047683716,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.992900013923645,"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":0.807768702507019},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7073243260383606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6529110074043274},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5293344259262085},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4663132131099701},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.43279343843460083},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.41115936636924744},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39057639241218567},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38835930824279785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37744566798210144},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35579150915145874},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16353866457939148},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11403045058250427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807768702507019},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7073243260383606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6529110074043274},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5293344259262085},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4663132131099701},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.43279343843460083},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.41115936636924744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39057639241218567},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38835930824279785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37744566798210144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35579150915145874},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16353866457939148},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11403045058250427},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2408279554","https://openalex.org/W2507296351","https://openalex.org/W2772955562","https://openalex.org/W2884822772","https://openalex.org/W2896457183","https://openalex.org/W2964241181","https://openalex.org/W3030520226","https://openalex.org/W3033210410","https://openalex.org/W3035682985","https://openalex.org/W3094502228","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3137278571","https://openalex.org/W3138516171","https://openalex.org/W3138796575","https://openalex.org/W3139633126","https://openalex.org/W3145450063","https://openalex.org/W3156811085","https://openalex.org/W3157506437","https://openalex.org/W3163465952","https://openalex.org/W3170874841","https://openalex.org/W3172509117","https://openalex.org/W3183804933","https://openalex.org/W3186979696","https://openalex.org/W4212819272","https://openalex.org/W4214588794","https://openalex.org/W4214614183","https://openalex.org/W4226363321","https://openalex.org/W4313056180","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6753421600","https://openalex.org/W6778485988","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6795140394","https://openalex.org/W6796417832","https://openalex.org/W6797463666"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W1556451512","https://openalex.org/W4234091740","https://openalex.org/W4213350282","https://openalex.org/W2230171082","https://openalex.org/W2583128298","https://openalex.org/W2369125128","https://openalex.org/W2022275305","https://openalex.org/W2134423494","https://openalex.org/W3160236137"],"abstract_inverted_index":{"Following":[0],"the":[1,6,14,23,33,48,63,89,107],"success":[2,20],"in":[3,13,32],"language":[4],"domain,":[5],"self-attention":[7],"mechanism":[8],"(Transformer)":[9],"has":[10],"been":[11,42,59],"adopted":[12],"vision":[15,34,73,121],"domain":[16,35],"and":[17,51,55,80,92],"achieving":[18],"great":[19],"recently.":[21],"Additionally,":[22],"use":[24],"of":[25,120],"multi-layer":[26],"perceptron":[27],"(MLP)":[28],"is":[29,93,103],"also":[30],"explored":[31],"as":[36],"another":[37],"stream.":[38],"These":[39],"architectures":[40],"have":[41,58],"attracting":[43],"attention":[44],"recently":[45],"to":[46,83,88,97],"alternate":[47],"traditional":[49],"CNNs,":[50],"many":[52],"Vision":[53,56],"Transformers":[54],"MLPs":[57],"proposed.":[60],"By":[61],"fusing":[62],"above":[64],"two":[65],"streams,":[66],"this":[67],"paper":[68],"proposes":[69],"gSwin,":[70],"a":[71],"novel":[72],"model":[74,124],"which":[75],"can":[76,109],"consider":[77],"spatial":[78],"hierarchy":[79],"locality":[81],"due":[82,96],"its":[84,98],"network":[85],"structure":[86],"similar":[87],"Swin":[90,114],"Transformer,":[91],"parameter":[94],"efficient":[95],"gated":[99],"MLP-based":[100],"architecture.":[101],"It":[102],"experimentally":[104],"confirmed":[105],"that":[106],"gSwin":[108],"achieve":[110],"better":[111],"accuracy":[112],"than":[113],"Transformer":[115],"on":[116],"three":[117],"common":[118],"tasks":[119],"with":[122],"smaller":[123],"size.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-05-07T00:00:00"}