{"id":"https://openalex.org/W7125925965","doi":"https://doi.org/10.1109/tip.2026.3655121","title":"CAS-ViT: Convolutional Additive Self-Attention Vision Transformers for Efficient Mobile Applications","display_name":"CAS-ViT: Convolutional Additive Self-Attention Vision Transformers for Efficient Mobile Applications","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125925965","doi":"https://doi.org/10.1109/tip.2026.3655121","pmid":"https://pubmed.ncbi.nlm.nih.gov/41605148"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3655121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3655121","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":null,"display_name":"Tianfang Zhang","orcid":"https://orcid.org/0000-0003-4183-7053"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianfang Zhang","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4183-7053","affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124101343","display_name":"Lei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Washington, Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Washington, Seattle, United States","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124064543","display_name":"Yang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhou","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-1439-7282","affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124094251","display_name":"Wentao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Liu","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6587-9878","affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124136971","display_name":"Chen Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Qian","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8761-5563","affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124112227","display_name":"Jenq-Neng Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jenq-Neng Hwang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Washington, Seattle, United States"],"raw_orcid":"https://orcid.org/0000-0002-8877-2421","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Washington, Seattle, United States","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiangyang Ji","orcid":"https://orcid.org/0000-0002-7333-9975"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Ji","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7333-9975","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":38.715,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.99754442,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":null,"first_page":"1899","last_page":"1909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9553999900817871,"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":0.9553999900817871,"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":0.008200000040233135,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0035000001080334187,"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/security-token","display_name":"Security token","score":0.5752000212669373},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49320000410079956},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48890000581741333},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.4431999921798706},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.3601999878883362},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.35839998722076416},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3522999882698059},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3244999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989000082015991},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5752000212669373},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.4431999921798706},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3244999945163727},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32359999418258667},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2026.3655121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3655121","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:41605148","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41605148","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},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/aeab65bf-2180-4663-9705-c82159e038a8","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/aeab65bf-2180-4663-9705-c82159e038a8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhang , T , Li , L , Zhou , Y , Liu , W , Qian , C , Hwang , J N & Ji , X 2026 , ' CAS-ViT : Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications ' , IEEE Transactions on Image Processing , vol. 35 , pp. 1899-1909 . https://doi.org/10.1109/TIP.2026.3655121","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2086161653","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2507296351","https://openalex.org/W2549139847","https://openalex.org/W2752782242","https://openalex.org/W2910628332","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963351448","https://openalex.org/W2963925437","https://openalex.org/W2982083293","https://openalex.org/W3034429256","https://openalex.org/W3035682985","https://openalex.org/W3037492894","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3139049060","https://openalex.org/W3175515048","https://openalex.org/W4214493665","https://openalex.org/W4288325606","https://openalex.org/W4289752563","https://openalex.org/W4312443924","https://openalex.org/W4312820606","https://openalex.org/W4312881242","https://openalex.org/W4312950730","https://openalex.org/W4313007769","https://openalex.org/W4313170858","https://openalex.org/W4317794940","https://openalex.org/W4320036893","https://openalex.org/W4320036918","https://openalex.org/W4328027236","https://openalex.org/W4385245566","https://openalex.org/W4385652274","https://openalex.org/W4386075524","https://openalex.org/W4386076083","https://openalex.org/W4386076539","https://openalex.org/W4386568072","https://openalex.org/W4388145401","https://openalex.org/W4390872447","https://openalex.org/W4390872550","https://openalex.org/W4390872670","https://openalex.org/W4390874124","https://openalex.org/W4393404507","https://openalex.org/W4394597260","https://openalex.org/W4394597781","https://openalex.org/W4402703046","https://openalex.org/W4402727337","https://openalex.org/W4404199198","https://openalex.org/W4409367296","https://openalex.org/W4413050942"],"related_works":[],"abstract_inverted_index":{"Vision":[0,58],"Transformers":[1],"(ViTs)":[2],"mark":[3],"a":[4,62,144,163,216],"revolutionary":[5],"advance":[6],"in":[7,46,68],"neural":[8],"networks":[9],"with":[10,186],"their":[11],"token":[12,21,78],"mixer's":[13],"powerful":[14],"global":[15,82],"context":[16],"capability.":[17],"However,":[18],"the":[19,75],"pairwise":[20],"affinity":[22],"and":[23,33,66,93,107,124,134,175,180,198,223,227],"complex":[24,118],"matrix":[25,122],"operations":[26,119],"limit":[27],"its":[28],"deployment":[29],"on":[30,86,190,195],"resource-constrained":[31],"scenarios":[32],"real-time":[34],"applications,":[35],"such":[36,90,120],"as":[37,91,110,121],"mobile":[38,69],"devices,":[39],"although":[40],"considerable":[41],"efforts":[42],"have":[43],"been":[44],"made":[45],"previous":[47],"works.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,72,97,142,159],"introduce":[53,127],"CAS-ViT:":[54],"Convolutional":[55,99,128],"Additive":[56,100,129],"Self-attention":[57],"Transformers,":[59],"to":[60,80,154,205],"achieve":[61],"balance":[63,218],"between":[64],"efficiency":[65],"performance":[67],"applications.":[70],"Firstly,":[71],"argue":[73],"that":[74,212],"capability":[76],"of":[77,146,165,219],"mixers":[79],"obtain":[81],"contextual":[83],"information":[84,88],"hinges":[85],"multiple":[87],"interactions,":[89],"spatial":[92,106],"channel":[94,108],"domains.":[95],"Subsequently,":[96],"propose":[98],"Token":[101],"Mixer":[102],"(CATM)":[103],"employing":[104],"underlying":[105],"attention":[109],"novel":[111],"interaction":[112],"forms.":[113],"This":[114],"module":[115],"eliminates":[116],"troublesome":[117],"multiplication":[123],"Softmax.":[125],"We":[126],"Self-attention(CAS)":[130],"block":[131],"hybrid":[132],"architecture":[133],"utilize":[135],"CATM":[136],"for":[137],"each":[138],"block.":[139],"And":[140],"further,":[141],"build":[143],"family":[145],"lightweight":[147],"networks,":[148],"which":[149],"can":[150],"be":[151],"easily":[152],"extended":[153],"various":[155],"downstream":[156],"tasks.":[157],"Finally,":[158],"evaluate":[160],"CAS-ViT":[161],"across":[162],"variety":[164],"vision":[166],"tasks,":[167],"including":[168],"image":[169],"classification,":[170],"object":[171],"detection,":[172],"instance":[173],"segmentation,":[174],"semantic":[176],"segmentation.":[177],"Our":[178,225],"M":[179],"T":[181],"model":[182,228],"achieves":[183,215],"83.0%/84.1%":[184],"top-1":[185],"only":[187],"12M/21M":[188],"parameters":[189],"ImageNet-1K.":[191],"Meanwhile,":[192],"throughput":[193],"evaluations":[194],"GPUs,":[196],"ONNX,":[197],"iPhones":[199],"also":[200],"demonstrate":[201,211],"superior":[202],"results":[203],"compared":[204],"other":[206],"state-of-the-art":[207],"backbones.":[208],"Extensive":[209],"experiments":[210],"our":[213],"approach":[214],"better":[217],"performance,":[220],"efficient":[221],"inference":[222],"easy-to-deploy.":[224],"code":[226],"are":[229],"available":[230],"at:":[231],"https://github.com/Tianfang-Zhang/CAS-ViT.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-01-29T00:00:00"}