{"id":"https://openalex.org/W4406208390","doi":"https://doi.org/10.1109/tpami.2024.3506283","title":"Foundation Models Defining a New Era in Vision: A Survey and Outlook","display_name":"Foundation Models Defining a New Era in Vision: A Survey and Outlook","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4406208390","doi":"https://doi.org/10.1109/tpami.2024.3506283","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030979"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3506283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3506283","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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":"Muhammad Awais","orcid":"https://orcid.org/0000-0003-2407-7865"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muhammad Awais","raw_affiliation_strings":["MBZ University of AI, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0003-2407-7865","affiliations":[{"raw_affiliation_string":"MBZ University of AI, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083105774","display_name":"Muzammal Naseer","orcid":"https://orcid.org/0000-0001-7663-7161"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE","AU","US"],"is_corresponding":false,"raw_author_name":"Muzammal Naseer","raw_affiliation_strings":["Computer Science Department and Center of Secure Cyber-Physical Security Systems, Khalifa University, Abu Dhabi, UAE","CECS, Australian National University, Canberra ACT, Australia","Computer Science Department of Georgia Institute of Technology, Atlanta, USA","Computer Science Department and Center of Secure Cyber-Physical Security Systems, Khalifa University, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-7663-7161","affiliations":[{"raw_affiliation_string":"Computer Science Department and Center of Secure Cyber-Physical Security Systems, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]},{"raw_affiliation_string":"CECS, Australian National University, Canberra ACT, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Computer Science Department of Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Computer Science Department and Center of Secure Cyber-Physical Security Systems, Khalifa University, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000300751","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-9502-1749"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","AU"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["MBZ University of AI, Abu Dhabi, UAE","CECS, Australian National University, Canberra ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9502-1749","affiliations":[{"raw_affiliation_string":"MBZ University of AI, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"CECS, Australian National University, Canberra ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022929869","display_name":"Rao Muhammad Anwer","orcid":"https://orcid.org/0000-0002-9041-2214"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Rao Muhammad Anwer","raw_affiliation_strings":["MBZ University of AI, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-9041-2214","affiliations":[{"raw_affiliation_string":"MBZ University of AI, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009362997","display_name":"Hisham Cholakkal","orcid":"https://orcid.org/0000-0002-8230-9065"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hisham Cholakkal","raw_affiliation_strings":["MBZ University of AI, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-8230-9065","affiliations":[{"raw_affiliation_string":"MBZ University of AI, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103215307","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0002-8216-1128"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-8216-1128","affiliations":[{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418319","display_name":"Ming\u2013Hsuan Yang","orcid":"https://orcid.org/0000-0003-4848-2304"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Hsuan Yang","raw_affiliation_strings":["University of California, Merced, CA, USA","Yonsei University, and Google Research, USA"],"raw_orcid":"https://orcid.org/0000-0003-4848-2304","affiliations":[{"raw_affiliation_string":"University of California, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"Yonsei University, and Google Research, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103881866","display_name":"Fahad Shahbaz Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","SE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["MBZ University of AI, Abu Dhabi, UAE","Computer Vision Laboratory, Link¨oping University, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-4263-3143","affiliations":[{"raw_affiliation_string":"MBZ University of AI, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Computer Vision Laboratory, Link¨oping University, Sweden","institution_ids":["https://openalex.org/I102134673"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":268.5274,"has_fulltext":false,"cited_by_count":216,"citation_normalized_percentile":{"value":0.99997176,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"47","issue":"4","first_page":"2245","last_page":"2264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991000294685364,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9527999758720398,"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":0.9157999753952026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7769436836242676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6225407123565674},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5370985269546509},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5039932131767273},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.48112693428993225},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4633754789829254},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4588414430618286},{"id":"https://openalex.org/keywords/vision-science","display_name":"Vision science","score":0.4212353527545929},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4170226752758026},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.41222119331359863},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.380776047706604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37868303060531616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3337400555610657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7769436836242676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6225407123565674},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5370985269546509},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5039932131767273},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48112693428993225},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4633754789829254},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4588414430618286},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.4212353527545929},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4170226752758026},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.41222119331359863},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.380776047706604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37868303060531616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3337400555610657},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3506283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3506283","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030979","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030979","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":199,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2056568601","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2561196672","https://openalex.org/W2565639579","https://openalex.org/W2886641317","https://openalex.org/W2896348597","https://openalex.org/W2963150697","https://openalex.org/W3035524453","https://openalex.org/W3090449556","https://openalex.org/W3138516171","https://openalex.org/W3172942063","https://openalex.org/W3173777717","https://openalex.org/W3174770825","https://openalex.org/W3176445421","https://openalex.org/W3213351348","https://openalex.org/W3216551675","https://openalex.org/W4205991051","https://openalex.org/W4214926101","https://openalex.org/W4225683910","https://openalex.org/W4312420092","https://openalex.org/W4312563428","https://openalex.org/W4312629998","https://openalex.org/W4312740349","https://openalex.org/W4312784228","https://openalex.org/W4312810944","https://openalex.org/W4312881242","https://openalex.org/W4312910992","https://openalex.org/W4312912313","https://openalex.org/W4312956471","https://openalex.org/W4312960937","https://openalex.org/W4312980231","https://openalex.org/W4313007769","https://openalex.org/W4313026212","https://openalex.org/W4313156423","https://openalex.org/W4360884927","https://openalex.org/W4362598512","https://openalex.org/W4376226279","https://openalex.org/W4378501037","https://openalex.org/W4383176792","https://openalex.org/W4385245566","https://openalex.org/W4385571689","https://openalex.org/W4385734161","https://openalex.org/W4386065512","https://openalex.org/W4386065691","https://openalex.org/W4386066015","https://openalex.org/W4386066126","https://openalex.org/W4386071707","https://openalex.org/W4386075997","https://openalex.org/W4386076084","https://openalex.org/W4386076112","https://openalex.org/W4386076522","https://openalex.org/W4389520191","https://openalex.org/W4389523832","https://openalex.org/W4390190606","https://openalex.org/W4390873481","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4392172801","https://openalex.org/W4394938913","https://openalex.org/W4402671735","https://openalex.org/W4403649914","https://openalex.org/W4407512410","https://openalex.org/W6620707391","https://openalex.org/W6637162671","https://openalex.org/W6676497082","https://openalex.org/W6733814495","https://openalex.org/W6739585900","https://openalex.org/W6739868092","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6766673545","https://openalex.org/W6766776083","https://openalex.org/W6766904570","https://openalex.org/W6769311223","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6779977557","https://openalex.org/W6784333009","https://openalex.org/W6784577980","https://openalex.org/W6788135285","https://openalex.org/W6789909235","https://openalex.org/W6790019176","https://openalex.org/W6790428460","https://openalex.org/W6790904380","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6797148833","https://openalex.org/W6797716411","https://openalex.org/W6798805250","https://openalex.org/W6800139874","https://openalex.org/W6800751262","https://openalex.org/W6802386650","https://openalex.org/W6802517928","https://openalex.org/W6802987763","https://openalex.org/W6803446505","https://openalex.org/W6803872405","https://openalex.org/W6803953248","https://openalex.org/W6809646742","https://openalex.org/W6810081322","https://openalex.org/W6810220367","https://openalex.org/W6810334672","https://openalex.org/W6810738896","https://openalex.org/W6810859482","https://openalex.org/W6811013733","https://openalex.org/W6811072154","https://openalex.org/W6811340617","https://openalex.org/W6838461927","https://openalex.org/W6838719481","https://openalex.org/W6838889364","https://openalex.org/W6839220867","https://openalex.org/W6839390831","https://openalex.org/W6839459284","https://openalex.org/W6839745749","https://openalex.org/W6842542540","https://openalex.org/W6842585177","https://openalex.org/W6842762852","https://openalex.org/W6843358153","https://openalex.org/W6843405348","https://openalex.org/W6844432065","https://openalex.org/W6846007759","https://openalex.org/W6846044722","https://openalex.org/W6846242362","https://openalex.org/W6846870107","https://openalex.org/W6847013730","https://openalex.org/W6847076894","https://openalex.org/W6848909144","https://openalex.org/W6849120541","https://openalex.org/W6849177959","https://openalex.org/W6849677550","https://openalex.org/W6849682869","https://openalex.org/W6850015000","https://openalex.org/W6850204008","https://openalex.org/W6850462617","https://openalex.org/W6850503672","https://openalex.org/W6850625674","https://openalex.org/W6850787431","https://openalex.org/W6850822301","https://openalex.org/W6850936240","https://openalex.org/W6850991314","https://openalex.org/W6851392053","https://openalex.org/W6851522027","https://openalex.org/W6851581138","https://openalex.org/W6851592950","https://openalex.org/W6851607685","https://openalex.org/W6851762504","https://openalex.org/W6851775633","https://openalex.org/W6851948999","https://openalex.org/W6851950068","https://openalex.org/W6851980744","https://openalex.org/W6852060543","https://openalex.org/W6852107595","https://openalex.org/W6852410717","https://openalex.org/W6852429019","https://openalex.org/W6852489829","https://openalex.org/W6852785562","https://openalex.org/W6852800892","https://openalex.org/W6852821026","https://openalex.org/W6852874933","https://openalex.org/W6852880106","https://openalex.org/W6852952677","https://openalex.org/W6852984070","https://openalex.org/W6852999659","https://openalex.org/W6853116092","https://openalex.org/W6853219587","https://openalex.org/W6853251322","https://openalex.org/W6853274917","https://openalex.org/W6853308660","https://openalex.org/W6853313673","https://openalex.org/W6853369525","https://openalex.org/W6853515732","https://openalex.org/W6853526317","https://openalex.org/W6853646231","https://openalex.org/W6853821718","https://openalex.org/W6853838016","https://openalex.org/W6854005609","https://openalex.org/W6854078521","https://openalex.org/W6854222408","https://openalex.org/W6854263694","https://openalex.org/W6854315368","https://openalex.org/W6854362512","https://openalex.org/W6854511533","https://openalex.org/W6854518852","https://openalex.org/W6854595082","https://openalex.org/W6855009501","https://openalex.org/W6855795293","https://openalex.org/W6855815363","https://openalex.org/W6856037140","https://openalex.org/W6858288548","https://openalex.org/W6858508493","https://openalex.org/W6858564163","https://openalex.org/W6860555993","https://openalex.org/W6861989417","https://openalex.org/W6862205494","https://openalex.org/W6862257250","https://openalex.org/W6866442993"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W2905433371","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2888392564"],"abstract_inverted_index":{"Vision":[0],"systems":[1],"that":[2],"see":[3],"and":[4,24,28,46,52,64,72,162,169,176,190,206,226],"reason":[5],"about":[6,115],"the":[7,31,59,123,163,173],"compositional":[8],"nature":[9],"of":[10,88,137,198,220,222],"visual":[11],"scenes":[12],"are":[13,80],"fundamental":[14],"to":[15,57,82,146,203],"understanding":[16],"our":[17],"world.":[18],"The":[19,54,86],"complex":[20],"relations":[21],"between":[22,61],"objects":[23],"their":[25,188,194],"locations,":[26],"ambiguities,":[27],"variations":[29],"in":[30,38,182,187,193,213],"real-world":[32,195],"environment":[33],"can":[34,91],"be":[35,92],"better":[36],"described":[37],"human":[39],"language,":[40],"naturally":[41],"governed":[42],"by":[43,104,112],"grammatical":[44],"rules":[45],"other":[47],"modalities":[48,63,149],"such":[49,62,89,138],"as":[50,83],"audio":[51],"depth.":[53],"models":[55,79,90,181,224],"learned":[56],"bridge":[58],"gap":[60],"large-scale":[65],"training":[66,154],"data":[67],"facilitate":[68],"contextual":[69,199],"reasoning,":[70],"generalization,":[71],"prompt":[73],"capabilities":[74],"at":[75],"test":[76],"time.":[77],"These":[78],"referred":[81],"foundation":[84,140,180,223],"models.":[85],"output":[87],"modified":[93],"through":[94,126],"human-provided":[95],"prompts":[96],"without":[97],"retraining,":[98],"e.g.,":[99],"segmenting":[100],"a":[101,106,134,217],"particular":[102],"object":[103],"providing":[105],"bounding":[107],"box,":[108],"having":[109],"interactive":[110],"dialogues":[111],"asking":[113],"questions":[114],"an":[116],"image":[117],"or":[118,121],"video":[119],"scene":[120],"manipulating":[122],"robot's":[124],"behavior":[125],"language":[127],"instructions.":[128],"In":[129],"this":[130,214],"survey,":[131],"we":[132],"provide":[133],"comprehensive":[135],"review":[136,210],"emerging":[139],"models,":[141],"including":[142,185],"typical":[143],"architecture":[144],"designs":[145],"combine":[147],"different":[148],"(vision,":[150],"text,":[151],"audio,":[152],"etc.),":[153],"objectives":[155],"(contrastive,":[156],"generative),":[157],"pre-training":[158],"datasets,":[159],"fine-tuning":[160],"mechanisms,":[161],"common":[164],"prompting":[165],"patterns;":[166],"textual,":[167],"visual,":[168],"heterogeneous.":[170],"We":[171,209],"discuss":[172],"open":[174],"challenges":[175],"research":[177],"directions":[178],"for":[179],"computer":[183],"vision,":[184],"difficulties":[186],"evaluations":[189],"benchmarking,":[191],"gaps":[192],"understanding,":[196,200],"limitations":[197],"biases,":[201],"vulnerability":[202],"adversarial":[204],"attacks,":[205],"interpretability":[207],"issues.":[208],"recent":[211],"developments":[212],"field,":[215],"covering":[216],"wide":[218],"range":[219],"applications":[221],"systematically":[225],"comprehensively.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":99},{"year":2025,"cited_by_count":115},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}