{"id":"https://openalex.org/W4417172182","doi":"https://doi.org/10.1109/iccv51701.2025.01660","title":"FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models","display_name":"FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417172182","doi":"https://doi.org/10.1109/iccv51701.2025.01660"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.20860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103250942","display_name":"Mainak Singha","orcid":"https://orcid.org/0000-0002-7615-2575"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mainak Singha","raw_affiliation_strings":["University of Trento,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento,Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037398393","display_name":"Subhankar Roy","orcid":"https://orcid.org/0009-0008-2395-8111"},"institutions":[{"id":"https://openalex.org/I11039511","display_name":"University of Bergamo","ror":"https://ror.org/02mbd5571","country_code":"IT","type":"education","lineage":["https://openalex.org/I11039511"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Subhankar Roy","raw_affiliation_strings":["University of Bergamo,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bergamo,Italy","institution_ids":["https://openalex.org/I11039511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104278316","display_name":"Sarthak Mehrotra","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarthak Mehrotra","raw_affiliation_strings":["Indian Institute of Technology Bombay,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101451817","display_name":"Ankit Jha","orcid":"https://orcid.org/0000-0002-1063-8978"},"institutions":[{"id":"https://openalex.org/I33552525","display_name":"LNM Institute of Information Technology","ror":"https://ror.org/03jp7rg16","country_code":"IN","type":"education","lineage":["https://openalex.org/I33552525"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankit Jha","raw_affiliation_strings":["LNMIIT,Jaipur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LNMIIT,Jaipur,India","institution_ids":["https://openalex.org/I33552525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014000715","display_name":"Moloud Abdar","orcid":"https://orcid.org/0000-0002-3059-6357"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Moloud Abdar","raw_affiliation_strings":["The University of Queensland,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland,Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020786167","display_name":"Biplab Banerjee","orcid":"https://orcid.org/0000-0001-8371-8138"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Biplab Banerjee","raw_affiliation_strings":["Indian Institute of Technology Bombay,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065059558","display_name":"Elisa Ricci","orcid":"https://orcid.org/0000-0002-0228-1147"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisa Ricci","raw_affiliation_strings":["University of Trento,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento,Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8378999829292297,"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":0.8378999829292297,"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":0.11580000072717667,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.006399999838322401,"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/generalizability-theory","display_name":"Generalizability theory","score":0.7803000211715698},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7290999889373779},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6721000075340271},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6194000244140625},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5759000182151794},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5378999710083008},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4634999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226000070571899},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7803000211715698},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7290999889373779},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6721000075340271},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827999711036682},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5378999710083008},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4634999930858612},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37790000438690186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.01660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.20860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.20860","pdf_url":"https://arxiv.org/pdf/2504.20860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:zenodo.org:19110513","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2504.20860","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICCV","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.48550/arxiv.2504.20860","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.20860","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.20860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.20860","pdf_url":"https://arxiv.org/pdf/2504.20860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417172182.pdf","grobid_xml":"https://content.openalex.org/works/W4417172182.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"federated":[1],"learning,":[2],"textual":[3,44,85,103],"prompt":[4,45],"tuning":[5,12,46],"adapts":[6],"Vision-Language":[7],"Models":[8],"(e.g.,":[9],"CLIP)":[10],"by":[11,34,174],"lightweight":[13],"input":[14,82,119],"tokens":[15],"(or":[16],"prompts)":[17],"on":[18,74,142,156],"local":[19],"client":[20],"data,":[21],"while":[22],"keeping":[23],"network":[24],"weights":[25],"frozen.":[26],"After":[27],"training,":[28],"only":[29,153],"the":[30,35,38,72,81,92,121],"prompts":[31,73,116],"are":[32,117],"shared":[33],"clients":[36],"with":[37,129],"central":[39],"server":[40],"for":[41],"aggregation.":[42],"However,":[43],"suffers":[47],"from":[48,80],"overfitting":[49],"to":[50,56,120,166],"known":[51],"concepts,":[52],"limiting":[53],"its":[54],"generalizability":[55,165],"unseen":[57,167],"concepts.":[58],"To":[59],"address":[60],"this":[61],"limitation,":[62],"we":[63],"propose":[64],"Multimodal":[65],"Visual":[66],"Prompt":[67],"Tuning":[68],"(FedMVP)":[69],"that":[70,100,150],"conditions":[71],"multimodal":[75,114],"contextual":[76],"information":[77],"-":[78,180],"derived":[79],"image":[83],"and":[84,104,127,136,159,169],"attribute":[86],"features":[87,106],"of":[88,94,125,132,178],"a":[89,97,108,130,137,175],"class.":[90],"At":[91],"core":[93],"FedMVP":[95,151],"is":[96,183],"PromptFormer":[98],"module":[99],"synergistically":[101],"aligns":[102],"visual":[105,115],"through":[107],"cross-attention":[109],"mechanism.":[110],"The":[111],"dynamically":[112],"generated":[113],"then":[118],"frozen":[122],"vision":[123],"encoder":[124],"CLIP,":[126],"trained":[128],"combination":[131],"CLIP":[133],"similarity":[134],"loss":[135],"consistency":[138],"loss.":[139],"Extensive":[140],"evaluation":[141],"20":[143],"datasets,":[144],"spanning":[145],"three":[146],"generalization":[147],"settings,":[148],"demonstrates":[149],"not":[152],"preserves":[154],"performance":[155],"in-distribution":[157],"classes":[158,168],"domains,":[160,170],"but":[161],"also":[162],"displays":[163],"higher":[164],"surpassing":[171],"state-of-the-art":[172],"methods":[173],"notable":[176],"margin":[177],"+1.57%":[179],"2.26%.":[181],"Code":[182],"available":[184],"at":[185],"https://github.com/mainaksingha01/FedMVP.":[186]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}