{"id":"https://openalex.org/W4403488762","doi":"https://doi.org/10.3233/faia240476","title":"FMViT: A Multiple-Frequency Mixing Vision Transformer","display_name":"FMViT: A Multiple-Frequency Mixing Vision Transformer","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403488762","doi":"https://doi.org/10.3233/faia240476"},"language":"en","primary_location":{"id":"doi:10.3233/faia240476","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240476","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240476","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wei Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Tan","raw_affiliation_strings":["Institute for Intelligent Computing, Alibaba Group, ziyuan.tw@alibaba-inc.com, cangyu.gyf@alibaba-inc.com, xingtong.xxs@taobao.com"],"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Computing, Alibaba Group, ziyuan.tw@alibaba-inc.com, cangyu.gyf@alibaba-inc.com, xingtong.xxs@taobao.com","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026308395","display_name":"Yifeng Geng","orcid":"https://orcid.org/0000-0002-3257-2746"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Geng","raw_affiliation_strings":["Institute for Intelligent Computing, Alibaba Group, ziyuan.tw@alibaba-inc.com, cangyu.gyf@alibaba-inc.com, xingtong.xxs@taobao.com"],"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Computing, Alibaba Group, ziyuan.tw@alibaba-inc.com, cangyu.gyf@alibaba-inc.com, xingtong.xxs@taobao.com","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101763148","display_name":"Xuansong Xie","orcid":"https://orcid.org/0000-0002-3671-799X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuansong Xie","raw_affiliation_strings":["Institute for Intelligent Computing, Alibaba Group, ziyuan.tw@alibaba-inc.com, cangyu.gyf@alibaba-inc.com, xingtong.xxs@taobao.com"],"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Computing, Alibaba Group, ziyuan.tw@alibaba-inc.com, cangyu.gyf@alibaba-inc.com, xingtong.xxs@taobao.com","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":12.2437,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.99024042,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9710000157356262,"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"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9710000157356262,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9247000217437744,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/transformer","display_name":"Transformer","score":0.5168948173522949},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.4839901924133301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.34473639726638794},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.3364119529724121},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.3042643070220947},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.27239561080932617},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16817212104797363},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08982428908348083}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5168948173522949},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.4839901924133301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34473639726638794},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.3364119529724121},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3042643070220947},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.27239561080932617},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16817212104797363},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08982428908348083},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240476","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240476","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240476","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240476","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.550000011920929,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2864363823"],"abstract_inverted_index":{"The":[0],"transformer":[1],"model":[2],"has":[3,78],"gained":[4],"widespread":[5],"adoption":[6],"in":[7,11,41,45,167,188,212,222],"computer":[8],"vision":[9,174],"tasks":[10],"recent":[12,61],"times.":[13],"However,":[14],"due":[15],"to":[16,28,66,71,114,144,233],"the":[17,29,98,147,177,192,226],"quadratic":[18],"time":[19],"and":[20,53,106,118,139,150,163],"memory":[21],"complexity":[22],"of":[23,31,131,169],"self-attention,":[24],"which":[25],"is":[26],"proportional":[27],"number":[30],"input":[32],"tokens,":[33],"most":[34],"existing":[35,160],"Vision":[36],"Transformers":[37],"(ViTs)":[38],"encounter":[39],"challenges":[40],"achieving":[42],"efficient":[43,89],"performance":[44,77,149,204],"practical":[46],"industrial":[47],"deployment":[48],"scenarios,":[49],"such":[50,127],"as":[51,128],"TensorRT":[52,178],"CoreML,":[54,216],"where":[55],"traditional":[56],"CNNs":[57],"excel.":[58],"Although":[59],"some":[60],"attempts":[62],"have":[63],"been":[64],"made":[65],"design":[67],"CNN-Transformer":[68,164],"hybrid":[69,90,165],"architectures":[70,166],"tackle":[72,83],"this":[73],"problem,":[74],"their":[75],"overall":[76],"not":[79],"met":[80],"expectations.":[81],"To":[82],"these":[84],"challenges,":[85],"we":[86,123],"propose":[87],"an":[88],"ViT":[91],"architecture":[92],"named":[93],"FMViT.":[94],"This":[95],"approach":[96],"enhances":[97],"model\u2019s":[99,148],"expressive":[100],"power":[101],"by":[102,183,220],"blending":[103],"high-frequency":[104],"features":[105,108],"low-frequency":[107],"with":[109,205,208,229],"varying":[110],"frequencies,":[111],"enabling":[112],"it":[113],"capture":[115],"both":[116],"local":[117],"global":[119],"information":[120],"effectively.":[121],"Additionally,":[122],"introduce":[124],"deploy-friendly":[125],"mechanisms":[126],"Multiple":[129],"groups":[130],"MLP":[132],"(gMLP)":[133],"Reparameterization,":[134],"Lightweight":[135],"Multi-head":[136],"Self-Attention":[137],"(RLMHSA),":[138],"Convolutional":[140],"Fusion":[141],"Block":[142],"(CFB)":[143],"further":[145],"improve":[146],"reduce":[151],"computational":[152],"overhead.":[153],"Our":[154],"experiments":[155],"demonstrate":[156],"that":[157],"FMViT":[158,180,201,217],"surpasses":[159],"CNNs,":[161],"ViTs,":[162],"terms":[168],"latency/accuracy":[170],"trade-offs":[171],"for":[172],"various":[173],"tasks.":[175],"On":[176,215],"platform,":[179],"outperforms":[181,218],"Resnet101":[182],"2.5%":[184],"(83.3%":[185],"vs.":[186,236],"80.8%)":[187],"top-1":[189,223],"accuracy":[190,224],"on":[191,225],"ImageNet":[193,227],"dataset":[194],"while":[195],"maintaining":[196],"similar":[197],"inference":[198,213,230],"latency.":[199],"Moreover,":[200],"achieves":[202],"comparable":[203,232],"EfficientNet-B5":[206],"but":[207],"a":[209],"43%":[210],"improvement":[211],"speed.":[214],"MobileOne":[219,234],"2.6%":[221],"dataset,":[228],"latency":[231],"(78.5%":[235],"75.9%).":[237]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}