{"id":"https://openalex.org/W4414458650","doi":"https://doi.org/10.1109/tcsvt.2025.3613794","title":"Fine-Tuning via Linked Domains: A Closed-Form Dual Alignment Mechanism for Transferring Vision-Language Models","display_name":"Fine-Tuning via Linked Domains: A Closed-Form Dual Alignment Mechanism for Transferring Vision-Language Models","publication_year":2025,"publication_date":"2025-09-24","ids":{"openalex":"https://openalex.org/W4414458650","doi":"https://doi.org/10.1109/tcsvt.2025.3613794"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3613794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3613794","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://openaccess.city.ac.uk/id/eprint/36226/1/Fine_Tuning_via_Linked_Domains__A_Closed_Form_Dual_Alignment_Mechanism_for_Transferring_Vision_Language_Models.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079874387","display_name":"Peiyu Lu","orcid":"https://orcid.org/0009-0005-2645-0717"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyu Lu","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou, China","School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2645-0717","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]},{"raw_affiliation_string":"School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758186","display_name":"Xiaoxu Li","orcid":"https://orcid.org/0000-0001-8833-9401"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxu Li","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou, China","School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]},{"raw_affiliation_string":"School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041649804","display_name":"Rui Zhu","orcid":"https://orcid.org/0000-0002-9944-0369"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rui Zhu","raw_affiliation_strings":["Faculty of Actuarial Science and Insurance, Bayes Business School, City St George&#x2019;s, University of London, London, U.K","Bayes Business School, Faculty of Actuarial Science and Insurance, City St George&#x2019;s, University of London, UK"],"raw_orcid":"https://orcid.org/0000-0002-9944-0369","affiliations":[{"raw_affiliation_string":"Faculty of Actuarial Science and Insurance, Bayes Business School, City St George&#x2019;s, University of London, London, U.K","institution_ids":["https://openalex.org/I180825142"]},{"raw_affiliation_string":"Bayes Business School, Faculty of Actuarial Science and Insurance, City St George&#x2019;s, University of London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","School of Artificial Intelligence, Pattern Recognition and Intelligent System Laboratory, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2950-2488","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Pattern Recognition and Intelligent System Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101752376","display_name":"Jie Cao","orcid":"https://orcid.org/0009-0007-5839-3416"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Cao","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou, China","School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]},{"raw_affiliation_string":"School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079361172","display_name":"Jing\u2010Hao Xue","orcid":"https://orcid.org/0000-0003-1174-610X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jing-Hao Xue","raw_affiliation_strings":["Department of Statistical Science, University College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1174-610X","affiliations":[{"raw_affiliation_string":"Department of Statistical Science, University College London, London, U.K","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22861874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"3","first_page":"3613","last_page":"3623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9103000164031982,"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":0.9103000164031982,"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/focus","display_name":"Focus (optics)","score":0.6568999886512756},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6211000084877014},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5601000189781189},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5322999954223633},{"id":"https://openalex.org/keywords/de-facto","display_name":"De facto","score":0.3912999927997589},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.37709999084472656},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.35830000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126999735832214},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6211000084877014},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C32277403","wikidata":"https://www.wikidata.org/wiki/Q740445","display_name":"Ridge","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcsvt.2025.3613794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3613794","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:openaccess.city.ac.uk:36226","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/rui=2Ezhu.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/36226/1/Fine_Tuning_via_Linked_Domains__A_Closed_Form_Dual_Alignment_Mechanism_for_Transferring_Vision_Language_Models.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"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":"Article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10214695","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10214695/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology       (2025)     (In press).","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:openaccess.city.ac.uk:36226","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/rui=2Ezhu.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/36226/1/Fine_Tuning_via_Linked_Domains__A_Closed_Form_Dual_Alignment_Mechanism_for_Transferring_Vision_Language_Models.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"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":"Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G172479822","display_name":null,"funder_award_id":"62225601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3150967382","display_name":null,"funder_award_id":"SZX2020034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3178831262","display_name":null,"funder_award_id":"62176110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8677236040","display_name":null,"funder_award_id":"U23B2052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320313889","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325188","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414458650.pdf","grobid_xml":"https://content.openalex.org/works/W4414458650.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Adapters":[0],"and":[1,58],"prompt":[2],"learning":[3],"have":[4],"become":[5],"two":[6],"de":[7],"facto":[8],"strategies":[9,49],"to":[10,113],"fine-tune":[11],"pre-trained":[12,41],"vision-language":[13],"models,":[14],"mitigating":[15],"the":[16,31,34,40,44,59,86,97,130],"high":[17],"computational":[18],"cost":[19],"of":[20,47,61,99,121],"fine-tuning":[21],"an":[22],"entire":[23],"model":[24,36],"for":[25],"downstream":[26],"tasks.":[27],"They":[28],"can":[29],"align":[30],"prediction":[32],"from":[33,39],"fine-tuned":[35],"with":[37],"that":[38,80,127],"model.":[42],"However,":[43],"existing":[45],"methods":[46,132],"these":[48],"primarily":[50],"focus":[51],"on":[52,133],"aligning":[53],"within":[54,90],"a":[55,74,91,118],"single":[56,92],"modality,":[57],"exploration":[60],"bidirectional":[62],"interactions":[63],"between":[64],"modalities":[65],"remains":[66],"limited.":[67],"To":[68],"address":[69],"this":[70],"issue,":[71],"we":[72],"propose":[73],"closed-form":[75,111],"dual":[76],"alignment":[77,98],"mechanism":[78],"(DAM)":[79],"<italic":[81],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">not":[83],"only":[84],"ensures":[85],"consistency":[87],"in":[88],"predictions":[89],"modality":[93],"but":[94],"also":[95],"achieves":[96],"features":[100],"across":[101],"different":[102],"modalities</i>.":[103],"In":[104],"DAM,":[105],"all":[106],"alignments":[107],"are":[108,142],"achieved":[109],"by":[110],"solutions":[112],"ridge":[114],"regression,":[115],"without":[116],"inducing":[117],"massive":[119],"number":[120],"learnable":[122],"parameters.":[123],"Experimental":[124],"results":[125],"demonstrate":[126],"DAM":[128],"outperforms":[129],"state-of-the-art":[131],"11":[134],"benchmarks":[135],"over":[136],"various":[137],"evaluation":[138],"metrics.":[139],"Our":[140],"codes":[141],"available":[143],"at":[144],"https://github.com/Peiy-Lu/DAM.":[145]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
