{"id":"https://openalex.org/W4416214876","doi":"https://doi.org/10.1109/tmm.2025.3632653","title":"How Vision-Language Tasks Benefit From Large Pre-Trained Models: A Survey","display_name":"How Vision-Language Tasks Benefit From Large Pre-Trained Models: A Survey","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416214876","doi":"https://doi.org/10.1109/tmm.2025.3632653"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3632653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632653","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008274338","display_name":"Yayun Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yayun Qi","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","School of Computer Science, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101422844","display_name":"LI Hong-xi","orcid":"https://orcid.org/0000-0002-8319-9427"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxi Li","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","School of Computer Science, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062837813","display_name":"Yena Song","orcid":"https://orcid.org/0000-0002-0861-1397"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqi Song","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","School of Computer Science, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011070646","display_name":"Xinxiao Wu","orcid":"https://orcid.org/0000-0002-2056-6947"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxiao Wu","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","School of Computer Science, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008274338"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3667434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"1188","last_page":"1210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9846000075340271,"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":0.9846000075340271,"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":0.00139999995008111,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0012000000569969416,"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/mainstream","display_name":"Mainstream","score":0.4943999946117401},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.40700000524520874},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.3935000002384186},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3253999948501587},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.30169999599456787},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.2879999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820900022983551},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5881999731063843},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35589998960494995},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3632653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632653","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":158,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1949478088","https://openalex.org/W1956340063","https://openalex.org/W1977295328","https://openalex.org/W2047643928","https://openalex.org/W2078238240","https://openalex.org/W2080133951","https://openalex.org/W2081580037","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2489434015","https://openalex.org/W2506483933","https://openalex.org/W2561715562","https://openalex.org/W2732026016","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2891394954","https://openalex.org/W2896457183","https://openalex.org/W2897857500","https://openalex.org/W2904565150","https://openalex.org/W2947312908","https://openalex.org/W2948672349","https://openalex.org/W2954199749","https://openalex.org/W2962770929","https://openalex.org/W2962990649","https://openalex.org/W2963092440","https://openalex.org/W2963115613","https://openalex.org/W2963398599","https://openalex.org/W2963536419","https://openalex.org/W2963540523","https://openalex.org/W2963622213","https://openalex.org/W2963656855","https://openalex.org/W2963743213","https://openalex.org/W2963890755","https://openalex.org/W2963936013","https://openalex.org/W2964303913","https://openalex.org/W2970327218","https://openalex.org/W2989322838","https://openalex.org/W2990307191","https://openalex.org/W2990330438","https://openalex.org/W2997762001","https://openalex.org/W3034493371","https://openalex.org/W3034727271","https://openalex.org/W3035356601","https://openalex.org/W3035552787","https://openalex.org/W3143320354","https://openalex.org/W3173859428","https://openalex.org/W3180355996","https://openalex.org/W3185341429","https://openalex.org/W3193171560","https://openalex.org/W3196798856","https://openalex.org/W3199693760","https://openalex.org/W3202408265","https://openalex.org/W3202473058","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W3217340782","https://openalex.org/W4226271114","https://openalex.org/W4281633937","https://openalex.org/W4285191490","https://openalex.org/W4304091651","https://openalex.org/W4304092183","https://openalex.org/W4312261477","https://openalex.org/W4312299632","https://openalex.org/W4312338297","https://openalex.org/W4312376880","https://openalex.org/W4312438583","https://openalex.org/W4312522167","https://openalex.org/W4312810944","https://openalex.org/W4312846625","https://openalex.org/W4312890493","https://openalex.org/W4312933868","https://openalex.org/W4312938727","https://openalex.org/W4319299894","https://openalex.org/W4320002812","https://openalex.org/W4379929801","https://openalex.org/W4385567053","https://openalex.org/W4385574156","https://openalex.org/W4385768038","https://openalex.org/W4385801730","https://openalex.org/W4386065691","https://openalex.org/W4386066010","https://openalex.org/W4386075661","https://openalex.org/W4386076015","https://openalex.org/W4386076029","https://openalex.org/W4386566667","https://openalex.org/W4387968214","https://openalex.org/W4389518764","https://openalex.org/W4389519086","https://openalex.org/W4389519568","https://openalex.org/W4389519587","https://openalex.org/W4389519987","https://openalex.org/W4389520080","https://openalex.org/W4389520252","https://openalex.org/W4389520282","https://openalex.org/W4390190606","https://openalex.org/W4390872395","https://openalex.org/W4390872424","https://openalex.org/W4390872747","https://openalex.org/W4390873015","https://openalex.org/W4390873321","https://openalex.org/W4390874161","https://openalex.org/W4390889743","https://openalex.org/W4391136507","https://openalex.org/W4391454481","https://openalex.org/W4392172801","https://openalex.org/W4393146968","https://openalex.org/W4393154592","https://openalex.org/W4393156223","https://openalex.org/W4393159130","https://openalex.org/W4393161084","https://openalex.org/W4401042436","https://openalex.org/W4401043215","https://openalex.org/W4401043604","https://openalex.org/W4402670135","https://openalex.org/W4402670323","https://openalex.org/W4402670859","https://openalex.org/W4402672066","https://openalex.org/W4402703029","https://openalex.org/W4402704595","https://openalex.org/W4402716035","https://openalex.org/W4402726948","https://openalex.org/W4402727624","https://openalex.org/W4402753770","https://openalex.org/W4402754009","https://openalex.org/W4402754023","https://openalex.org/W4402916777","https://openalex.org/W4402951693","https://openalex.org/W4402996663","https://openalex.org/W4403081466","https://openalex.org/W4403195962","https://openalex.org/W4403780727","https://openalex.org/W4404356490","https://openalex.org/W4404781941","https://openalex.org/W4404927209","https://openalex.org/W4405907214","https://openalex.org/W4406208390","https://openalex.org/W4410027467","https://openalex.org/W4410371768","https://openalex.org/W4410536678","https://openalex.org/W4411113244","https://openalex.org/W4411403346","https://openalex.org/W4412158322","https://openalex.org/W4416296080","https://openalex.org/W7103753941","https://openalex.org/W7108068597","https://openalex.org/W7133185086","https://openalex.org/W7133193597","https://openalex.org/W7133224126","https://openalex.org/W7133239427","https://openalex.org/W7133242627"],"related_works":[],"abstract_inverted_index":{"The":[0],"exploration":[1],"of":[2,29,49,57,68,72,93,127,148,154,184],"various":[3],"vision-language":[4,43,65,129,142,171],"tasks,":[5],"such":[6],"as":[7],"visual":[8,10,14],"captioning,":[9],"question":[11],"answering,":[12],"and":[13,24,45,75,116,144,190],"commonsense":[15],"reasoning,":[16],"is":[17,60],"an":[18],"important":[19],"area":[20],"in":[21,35,42,84,110,141,162,170],"artificial":[22],"intelligence":[23],"continuously":[25],"attracts":[26],"the":[27,30,47,55,62,69,90,102,146,152,159,168,176,181],"attention":[28,115],"research":[31,63,112,195],"community.":[32],"Despite":[33],"improvements":[34],"overall":[36],"performance,":[37],"classic":[38,103],"challenges":[39,140,169],"still":[40],"exist":[41],"tasks":[44,130,143],"hinder":[46],"development":[48],"this":[50,120],"area.":[51],"In":[52,119],"recent":[53,160],"years,":[54],"rise":[56],"pre-trained":[58,78,94,133,164,185],"models":[59,79,165],"driving":[61],"on":[64],"tasks.":[66,87,172],"Because":[67],"massive":[70],"scale":[71],"training":[73],"data":[74],"model":[76],"parameters,":[77],"have":[80,98,107],"exhibited":[81],"excellent":[82],"performance":[83],"numerous":[85],"downstream":[86],"Inspired":[88],"by":[89],"powerful":[91],"capabilities":[92],"models,":[95,186],"new":[96],"paradigms":[97],"emerged":[99],"to":[100,166,192],"solve":[101],"challenges.":[104],"Such":[105],"methods":[106],"become":[108],"mainstream":[109],"current":[111],"with":[113,180],"increasing":[114],"rapid":[117],"advances.":[118],"paper,":[121],"we":[122,136,157,174],"present":[123],"a":[124],"comprehensive":[125],"overview":[126],"how":[128],"benefit":[131],"from":[132],"models.":[134],"First,":[135],"review":[137],"several":[138],"main":[139],"discuss":[145,187],"limitations":[147,183],"previous":[149],"solutions":[150],"before":[151],"era":[153],"pre-training.":[155],"Next,":[156],"summarize":[158],"advances":[161],"incorporating":[163],"address":[167],"Finally,":[173],"analyze":[175],"potential":[177],"risks":[178],"associated":[179],"inherent":[182],"possible":[188],"solutions,":[189],"attempt":[191],"provide":[193],"future":[194],"directions.":[196]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-11-14T00:00:00"}