{"id":"https://openalex.org/W7225804513","doi":"https://doi.org/10.3390/app162211147","title":"The Architecture of Visual Foundation Models: A Comprehensive Review of Image, Video, and Multimodal Understanding","display_name":"The Architecture of Visual Foundation Models: A Comprehensive Review of Image, Video, and Multimodal Understanding","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225804513","doi":"https://doi.org/10.3390/app162211147"},"language":"en","primary_location":{"id":"doi:10.3390/app162211147","doi":"https://doi.org/10.3390/app162211147","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211147","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/app162211147","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080851325","display_name":"Abdussalam Elhanashi","orcid":"https://orcid.org/0000-0002-2514-1585","observed_orcids":["https://orcid.org/0000-0002-2514-1585"]},"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"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Abdussalam Elhanashi","raw_affiliation_strings":["Dipartimento Ingegneria dell\u2019Informazione, University of Pisa, 56126 Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2514-1585","affiliations":[{"raw_affiliation_string":"Dipartimento Ingegneria dell\u2019Informazione, University of Pisa, 56126 Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102026679","display_name":"Qinghe Zheng","orcid":"https://orcid.org/0000-0003-1466-2542","observed_orcids":["https://orcid.org/0000-0003-1466-2542","https://orcid.org/0000-0001-8037-7323","https://orcid.org/0009-0003-9628-8546"]},"institutions":[{"id":"https://openalex.org/I4210097214","display_name":"Shandong Management University","ror":"https://ror.org/00vzprm14","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210097214"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghe Zheng","raw_affiliation_strings":["School of Intelligent Engineering, Shandong Management University, Jinan 250357, China"],"raw_orcid":"https://orcid.org/0000-0001-8037-7323","affiliations":[{"raw_affiliation_string":"School of Intelligent Engineering, Shandong Management University, Jinan 250357, China","institution_ids":["https://openalex.org/I4210097214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091706301","display_name":"Sergio Saponara","orcid":"https://orcid.org/0000-0001-6724-4219","observed_orcids":["https://orcid.org/0000-0001-6724-4219"]},"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"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sergio Saponara","raw_affiliation_strings":["Dipartimento Ingegneria dell\u2019Informazione, University of Pisa, 56126 Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6724-4219","affiliations":[{"raw_affiliation_string":"Dipartimento Ingegneria dell\u2019Informazione, University of Pisa, 56126 Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080851325"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"22","first_page":"11147","last_page":"11147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9115999937057495,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9115999937057495,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06809999793767929,"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":0.017500000074505806,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5212000012397766},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4027000069618225},{"id":"https://openalex.org/C120060458","wikidata":"https://www.wikidata.org/wiki/Q10145","display_name":"Milestone","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3474000096321106},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/app162211147","doi":"https://doi.org/10.3390/app162211147","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211147","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/app162211147","doi":"https://doi.org/10.3390/app162211147","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211147","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2619082050","https://openalex.org/W2625366777","https://openalex.org/W2963341956","https://openalex.org/W3030520226","https://openalex.org/W3035524453","https://openalex.org/W3119997354","https://openalex.org/W3138516171","https://openalex.org/W3147387781","https://openalex.org/W3159481202","https://openalex.org/W3172942063","https://openalex.org/W4225683910","https://openalex.org/W4226002507","https://openalex.org/W4226167525","https://openalex.org/W4229081350","https://openalex.org/W4288083516","https://openalex.org/W4304013646","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312933868","https://openalex.org/W4313026212","https://openalex.org/W4385453669","https://openalex.org/W4386071707","https://openalex.org/W4386076428","https://openalex.org/W4386076522","https://openalex.org/W4389519587","https://openalex.org/W4390872297","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4395055639","https://openalex.org/W4396983117","https://openalex.org/W4400229207","https://openalex.org/W4402671548","https://openalex.org/W4402713111","https://openalex.org/W4402727359","https://openalex.org/W4402727760","https://openalex.org/W4402727764","https://openalex.org/W4404356490","https://openalex.org/W4404612908","https://openalex.org/W4406208390","https://openalex.org/W4413147844","https://openalex.org/W4415795395","https://openalex.org/W4415796627","https://openalex.org/W7128225325","https://openalex.org/W7133185515","https://openalex.org/W7133193597"],"related_works":[],"abstract_inverted_index":{"Research":[0],"in":[1,185,206,242],"visual":[2],"intelligence":[3],"has":[4],"shifted":[5],"from":[6],"task-specific":[7],"convolutional":[8],"networks":[9],"trained":[10],"on":[11],"curated":[12],"labels":[13],"toward":[14],"large-scale":[15],"pretrained":[16],"architectures":[17],"that":[18,223],"transfer":[19],"across":[20],"image,":[21,33],"video,":[22,34],"and":[23,35,49,70,76,85,110,122,128,146,151,169,212,230,248,251],"language":[24],"tasks":[25],"with":[26,81],"minimal":[27],"fine-tuning.":[28],"Existing":[29],"surveys":[30],"typically":[31],"treat":[32],"multimodal":[36,186,213],"foundation":[37],"models":[38,113,208],"as":[39,219],"separate":[40],"literatures,":[41],"or":[42],"compare":[43],"them":[44],"mainly":[45],"by":[46,238],"topic":[47],"breadth":[48],"model":[50],"count.":[51],"This":[52],"review":[53,236],"instead":[54],"reads":[55],"the":[56,71,87,90,97,101,180,199],"three":[57,61],"literatures":[58],"jointly":[59],"against":[60],"explicit":[62,82],"research":[63],"questions":[64],"concerning":[65],"architectural":[66],"convergence,":[67],"efficiency-versus-scale":[68],"trade-offs,":[69],"cross-modal":[72,143],"diffusion":[73],"of":[74,89,139,149],"techniques,":[75],"documents":[77],"its":[78],"literature-selection":[79,134],"procedure":[80],"retention":[83],"criteria":[84],"reports":[86],"composition":[88],"retained":[91],"literature.":[92],"Representative":[93],"systems":[94],"analyzed":[95],"include":[96],"Vision":[98],"Transformer,":[99],"CLIP,":[100],"Segment":[102],"Anything":[103],"family":[104],"(through":[105,114],"SAM":[106],"3),":[107],"DINOv3,":[108],"masked":[109],"joint-embedding":[111],"predictive":[112],"V-JEPA":[115],"2),":[116],"Flamingo,":[117],"BLIP-2,":[118],"LLaVA,":[119],"Chameleon,":[120],"Qwen2.5-VL,":[121],"GPT-4V,":[123],"consolidated":[124],"into":[125],"ten":[126],"tables":[127],"eight":[129],"original":[130],"figures,":[131],"including":[132],"a":[133,137,142,193,215,220],"flow":[135],"diagram,":[136],"comparison":[138],"learning":[140],"paradigms,":[141],"milestone":[144],"timeline,":[145],"mechanism-level":[147],"diagrams":[148],"video":[150,211],"vision-language":[152],"architectures.":[153],"Four":[154],"findings":[155],"emerge:":[156],"self-supervised":[157],"paradigms":[158],"progress":[159],"through":[160],"successive,":[161],"traceable":[162],"fixes":[163],"to":[164,204,255],"specific":[165],"predecessor":[166],"limitations;":[167],"connector-":[168],"distillation-based":[170],"efficiency":[171],"interventions":[172],"recover":[173],"performance":[174],"otherwise":[175],"requiring":[176],"substantially":[177],"more":[178],"parameters;":[179],"early-":[181],"versus":[182],"late-fusion":[183],"divergence":[184],"design":[187],"reflects":[188],"an":[189],"economic":[190],"rather":[191],"than":[192],"purely":[194],"technical":[195],"trade-off;":[196],"and,":[197],"within":[198],"sample":[200],"examined,":[201],"techniques":[202],"tend":[203],"appear":[205],"image":[207],"before":[209],"reaching":[210],"systems,":[214],"pattern":[216],"presented":[217],"here":[218],"testable":[221],"hypothesis":[222],"2025":[224],"releases":[225],"both":[226],"support":[227],"(V-JEPA":[228],"2)":[229],"qualify":[231],"(SAM":[232],"3,":[233],"Qwen2.5-VL).":[234],"The":[235],"closes":[237],"identifying":[239],"open":[240],"problems":[241],"temporal":[243],"reasoning,":[244],"hallucination,":[245],"computational":[246],"cost,":[247],"evaluation":[249],"validity,":[250],"outlines":[252],"directions":[253],"likely":[254],"shape":[256],"subsequent":[257],"research.":[258]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}