{"id":"https://openalex.org/W7160144492","doi":"https://doi.org/10.1016/j.cviu.2026.104791","title":"Self-attention as the backbone: A survey on Vision Transformers","display_name":"Self-attention as the backbone: A survey on Vision Transformers","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160144492","doi":"https://doi.org/10.1016/j.cviu.2026.104791"},"language":"en","primary_location":{"id":"doi:10.1016/j.cviu.2026.104791","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2026.104791","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.cviu.2026.104791","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135119195","display_name":"Ahmad Waseem","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]},{"id":"https://openalex.org/I159650629","display_name":"University of Sassari","ror":"https://ror.org/01bnjbv91","country_code":"IT","type":"education","lineage":["https://openalex.org/I159650629"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Ahmad Waseem","raw_affiliation_strings":["University of Pisa, Lungarno Pacinotti, 43, Pisa, 56126, Italy","University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Lungarno Pacinotti, 43, Pisa, 56126, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy","institution_ids":["https://openalex.org/I159650629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076411617","display_name":"Pietro Ruiu","orcid":"https://orcid.org/0000-0003-4420-3363"},"institutions":[{"id":"https://openalex.org/I159650629","display_name":"University of Sassari","ror":"https://ror.org/01bnjbv91","country_code":"IT","type":"education","lineage":["https://openalex.org/I159650629"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pietro Ruiu","raw_affiliation_strings":["University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy","institution_ids":["https://openalex.org/I159650629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026620789","display_name":"Seth Nixon","orcid":"https://orcid.org/0009-0005-0029-2319"},"institutions":[{"id":"https://openalex.org/I159650629","display_name":"University of Sassari","ror":"https://ror.org/01bnjbv91","country_code":"IT","type":"education","lineage":["https://openalex.org/I159650629"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Seth Nixon","raw_affiliation_strings":["University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy","institution_ids":["https://openalex.org/I159650629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084817805","display_name":"Andrea Lagorio","orcid":"https://orcid.org/0000-0001-9113-6103"},"institutions":[{"id":"https://openalex.org/I159650629","display_name":"University of Sassari","ror":"https://ror.org/01bnjbv91","country_code":"IT","type":"education","lineage":["https://openalex.org/I159650629"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Lagorio","raw_affiliation_strings":["University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy","institution_ids":["https://openalex.org/I159650629"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064744996","display_name":"M\u00e1ssimo Tistarelli","orcid":"https://orcid.org/0000-0002-3406-3048"},"institutions":[{"id":"https://openalex.org/I159650629","display_name":"University of Sassari","ror":"https://ror.org/01bnjbv91","country_code":"IT","type":"education","lineage":["https://openalex.org/I159650629"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Tistarelli","raw_affiliation_strings":["University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sassari, Piazza Universit\u00e0 1, Sassari, 07100, Italy","institution_ids":["https://openalex.org/I159650629"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5135119195"],"corresponding_institution_ids":["https://openalex.org/I108290504","https://openalex.org/I159650629"],"apc_list":{"value":2370,"currency":"USD","value_usd":2370},"apc_paid":{"value":2370,"currency":"USD","value_usd":2370},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5235243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"269","issue":null,"first_page":"104791","last_page":"104791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.18569999933242798,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.18569999933242798,"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/T10427","display_name":"Visual perception and processing mechanisms","score":0.08889999985694885,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.033900000154972076,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5371000170707703},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.33959999680519104},{"id":"https://openalex.org/keywords/artificial-vision","display_name":"Artificial vision","score":0.29330000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5529000163078308},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5371000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781000018119812},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4666000008583069},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.382099986076355},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C2982818900","wikidata":"https://www.wikidata.org/wiki/Q20779747","display_name":"Artificial vision","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.23829999566078186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.cviu.2026.104791","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2026.104791","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.cviu.2026.104791","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2026.104791","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F5497039910","display_name":"Ministero dell'Istruzione e del Merito","ror":"https://ror.org/01ehyh486"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":122,"referenced_works":["https://openalex.org/W1990283121","https://openalex.org/W2019370496","https://openalex.org/W2097117768","https://openalex.org/W2109255472","https://openalex.org/W2122710056","https://openalex.org/W2150593711","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2963163009","https://openalex.org/W2963341956","https://openalex.org/W2990818246","https://openalex.org/W3014641072","https://openalex.org/W3035422918","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3146366485","https://openalex.org/W3151130473","https://openalex.org/W3177318507","https://openalex.org/W3183430956","https://openalex.org/W3188427387","https://openalex.org/W4206706211","https://openalex.org/W4213019189","https://openalex.org/W4214493665","https://openalex.org/W4214588794","https://openalex.org/W4214614183","https://openalex.org/W4214634256","https://openalex.org/W4214654781","https://openalex.org/W4214709605","https://openalex.org/W4225672218","https://openalex.org/W4225829036","https://openalex.org/W4226224676","https://openalex.org/W4226424839","https://openalex.org/W4226512186","https://openalex.org/W4281918143","https://openalex.org/W4285163271","https://openalex.org/W4287020683","https://openalex.org/W4293680532","https://openalex.org/W4312340826","https://openalex.org/W4312599212","https://openalex.org/W4312726009","https://openalex.org/W4312769131","https://openalex.org/W4312769570","https://openalex.org/W4312805142","https://openalex.org/W4312812783","https://openalex.org/W4312849330","https://openalex.org/W4312950730","https://openalex.org/W4312957757","https://openalex.org/W4312960790","https://openalex.org/W4312986923","https://openalex.org/W4313007769","https://openalex.org/W4313156423","https://openalex.org/W4313160444","https://openalex.org/W4316021708","https://openalex.org/W4319663728","https://openalex.org/W4362692084","https://openalex.org/W4366352791","https://openalex.org/W4367663369","https://openalex.org/W4379382445","https://openalex.org/W4380082229","https://openalex.org/W4380520356","https://openalex.org/W4385346076","https://openalex.org/W4386047807","https://openalex.org/W4386065588","https://openalex.org/W4386065847","https://openalex.org/W4386075524","https://openalex.org/W4386075553","https://openalex.org/W4386075796","https://openalex.org/W4386076051","https://openalex.org/W4386076285","https://openalex.org/W4386076539","https://openalex.org/W4386076562","https://openalex.org/W4386083075","https://openalex.org/W4386083119","https://openalex.org/W4387338457","https://openalex.org/W4389977645","https://openalex.org/W4390189844","https://openalex.org/W4390660439","https://openalex.org/W4390872297","https://openalex.org/W4390872670","https://openalex.org/W4390873312","https://openalex.org/W4390873332","https://openalex.org/W4390874124","https://openalex.org/W4390874575","https://openalex.org/W4393156092","https://openalex.org/W4393950444","https://openalex.org/W4394625669","https://openalex.org/W4396794624","https://openalex.org/W4401817478","https://openalex.org/W4402660140","https://openalex.org/W4402727079","https://openalex.org/W4402727186","https://openalex.org/W4402727645","https://openalex.org/W4402727704","https://openalex.org/W4402727764","https://openalex.org/W4402753733","https://openalex.org/W4404741685","https://openalex.org/W4405197074","https://openalex.org/W4406208390","https://openalex.org/W4409387871","https://openalex.org/W4409917813","https://openalex.org/W4412077711","https://openalex.org/W4413144796","https://openalex.org/W4413144971","https://openalex.org/W4413145201","https://openalex.org/W4413145233","https://openalex.org/W4413145454","https://openalex.org/W4413145494","https://openalex.org/W4413145745","https://openalex.org/W4413145963","https://openalex.org/W4413146088","https://openalex.org/W4413146520","https://openalex.org/W4413146534","https://openalex.org/W4413146579","https://openalex.org/W4413158002","https://openalex.org/W4413857997","https://openalex.org/W4414032673","https://openalex.org/W7131088681","https://openalex.org/W7131114138","https://openalex.org/W7133197843"],"related_works":[],"abstract_inverted_index":{"The":[0],"human":[1],"cognitive":[2],"system":[3],"efficiently":[4],"processes":[5],"complex":[6],"environments":[7],"by":[8],"focusing":[9],"on":[10,58,104,131],"salient":[11],"regions,":[12],"inspiring":[13],"attention":[14,24,156,223],"mechanisms":[15],"that":[16,174],"amplify":[17],"critical":[18],"information.":[19],"Deep":[20],"learning":[21,77],"models":[22,53],"integrate":[23],"to":[25,118,191],"enhance":[26],"performance":[27,139],"across":[28,81],"tasks,":[29],"with":[30,116,157],"self-attention":[31,70,92,141,179,209,217],"gaining":[32],"prominence":[33],"through":[34,140,177],"its":[35,46],"remarkable":[36],"success":[37,44],"in":[38,48,225],"Transformer-based":[39,52],"natural":[40],"language":[41,194],"processing.":[42],"This":[43,164],"propelled":[45],"adoption":[47],"computer":[49],"vision,":[50],"where":[51,69],"surpass":[54],"conventional":[55],"deep":[56],"networks":[57],"multiple":[59],"benchmarks.":[60],"Recently,":[61],"large-scale":[62],"pretraining":[63],"has":[64,129],"enabled":[65],"vision":[66],"foundation":[67],"models,":[68,195],"acts":[71],"as":[72,151],"a":[73,167,214],"scalable":[74],"backbone":[75,172],"for":[76,160,185],"transferable":[78],"visual":[79],"representations":[80],"diverse":[82],"tasks.":[83],"By":[84],"modeling":[85],"global":[86],"dependencies":[87],"without":[88],"heavy":[89],"inductive":[90],"biases,":[91],"supports":[93],"flexible":[94],"and":[95,108,112,123,198,210,230,233,237],"expressive":[96],"representation":[97],"learning.":[98],"However,":[99],"Vision":[100],"Transformers":[101],"(ViTs)":[102],"rely":[103],"large":[105,193],"parameter":[106],"counts":[107],"high":[109],"computational":[110,133,231],"budgets,":[111],"their":[113,189],"quadratic":[114],"complexity":[115],"respect":[117],"input":[119],"size":[120],"restricts":[121],"scalability":[122],"real-world":[124],"deployment.":[125],"Consequently,":[126],"substantial":[127],"research":[128,239],"focused":[130],"reducing":[132],"overhead":[134],"while":[135],"preserving":[136],"or":[137,181],"improving":[138],"optimization.":[142],"In":[143],"parallel,":[144],"State":[145],"Space":[146],"Models":[147],"(SSMs)":[148],"have":[149],"emerged":[150],"an":[152],"alternative":[153],"paradigm,":[154],"replacing":[155],"linear-time":[158],"recurrence":[159],"efficient":[161],"long-range":[162],"modeling.":[163],"survey":[165],"provides":[166],"comprehensive":[168],"review":[169],"of":[170,216,227],"advanced":[171],"techniques":[173],"improve":[175],"ViTs":[176],"novel":[178],"designs":[180],"hybrid":[182],"integrations,":[183],"mainly":[184],"image":[186],"classification,":[187],"including":[188],"transfer":[190],"multimodal":[192],"generative":[196],"frameworks,":[197],"emerging":[199],"SSM-based":[200],"architectures,":[201],"alongside":[202],"ViT":[203],"explainability":[204],"approaches.":[205],"We":[206],"first":[207],"outline":[208],"Transformers,":[211],"then":[212],"introduce":[213],"taxonomy":[215],"variants.":[218],"Finally,":[219],"we":[220],"systematically":[221],"compare":[222],"architectures":[224],"terms":[226],"design,":[228],"accuracy,":[229],"efficiency,":[232],"discuss":[234],"current":[235],"limitations":[236],"future":[238],"directions.":[240]},"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-05-05T00:00:00"}