{"id":"https://openalex.org/W7154725174","doi":"https://doi.org/10.1109/tip.2026.3682113","title":"Ensemble Image and Text for Unsupervised Domain Adaptation Using Vision Language Models","display_name":"Ensemble Image and Text for Unsupervised Domain Adaptation Using Vision Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154725174","doi":"https://doi.org/10.1109/tip.2026.3682113","pmid":"https://pubmed.ncbi.nlm.nih.gov/41996433"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3682113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3682113","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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":"https://openalex.org/A5133872191","display_name":"Qi Jia","orcid":"https://orcid.org/0009-0001-8074-4178"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Jia","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0009-0001-8074-4178","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082047413","display_name":"Fei Du","orcid":"https://orcid.org/0000-0002-0776-819X"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Du","raw_affiliation_strings":["National Pilot School of Software, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-0776-819X","affiliations":[{"raw_affiliation_string":"National Pilot School of Software, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133836067","display_name":"Zulong Lin","orcid":"https://orcid.org/0009-0001-5313-9140"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zulong Lin","raw_affiliation_strings":["National Pilot School of Software, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0009-0001-5313-9140","affiliations":[{"raw_affiliation_string":"National Pilot School of Software, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133832318","display_name":"Jing Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Guo","raw_affiliation_strings":["National Pilot School of Software, Yunnan University, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Pilot School of Software, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100675701","display_name":"Yun Yang","orcid":"https://orcid.org/0000-0002-9893-3436"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Yang","raw_affiliation_strings":["National Pilot School of Software, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-9893-3436","affiliations":[{"raw_affiliation_string":"National Pilot School of Software, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4377992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"4091","last_page":"4105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3718999922275543,"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":0.3718999922275543,"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":0.19380000233650208,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07999999821186066,"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/domain-adaptation","display_name":"Domain adaptation","score":0.4909000098705292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48179998993873596},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4417000114917755},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.41510000824928284},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3684000074863434},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3409000039100647},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696999907493591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7488999962806702},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5264000296592712},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4909000098705292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.41510000824928284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39250001311302185},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3684000074863434},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3203999996185303},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.26489999890327454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3682113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3682113","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41996433","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41996433","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3918681972","display_name":null,"funder_award_id":"202401BC070006","funder_id":"https://openalex.org/F4320330387","funder_display_name":"Foundation for Fundamental Research of China"},{"id":"https://openalex.org/G6845129887","display_name":null,"funder_award_id":"62366055","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330387","display_name":"Foundation for Fundamental Research of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"Domain":[1],"Adaptation":[2],"(UDA)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,39,117,133],"pivotal":[8],"technique":[9,24],"for":[10,90,203],"enhancing":[11,44],"machine":[12],"learning":[13],"models'":[14],"performance":[15],"in":[16,64,113,185],"unlabeled":[17],"target":[18,36,58],"domain":[19,21,31,59,125,159],"with":[20,219],"shifts.":[22,126],"This":[23,145],"is":[25],"fundamentally":[26],"achieved":[27],"by":[28,128],"aligning":[29],"the":[30,52,66,150,169,182,232],"distributions":[32,60],"of":[33,154,173,234],"source":[34,56],"and":[35,57,212],"domains":[37,73],"within":[38],"latent":[40,68,76],"feature":[41,87],"space,":[42],"thereby":[43],"model":[45,135,167,190],"robustness":[46],"across":[47],"heterogeneous":[48],"data":[49],"distributions.":[50],"However,":[51],"inherent":[53,170],"discrepancy":[54],"between":[55],"poses":[61],"significant":[62],"challenges":[63],"identifying":[65],"optimal":[67],"space.":[69],"Furthermore,":[70],"projecting":[71],"both":[72],"into":[74,141],"suboptimal":[75],"spaces":[77],"may":[78],"induce":[79],"substantial":[80],"semantic":[81,107,152,164],"information":[82],"loss,":[83],"particularly":[84],"compromising":[85],"discriminative":[86],"representations":[88,103],"critical":[89],"final":[91],"tasks.":[92],"In":[93],"this":[94,129],"article,":[95],"our":[96,235],"systematic":[97],"analysis":[98],"reveals":[99],"that":[100,136],"natural":[101,114,119,155],"language":[102,120,156],"inherently":[104],"possess":[105],"stronger":[106],"abstraction":[108,171,218],"capabilities":[109],"than":[110],"visual":[111,139,210,220],"features":[112],"images.":[115],"As":[116],"result,":[118],"tends":[121],"to":[122,157,176,201],"have":[123],"smaller":[124],"Motivated":[127],"discovery,":[130],"we":[131],"proposed":[132],"novel":[134],"systematically":[137],"transforms":[138],"patterns":[140],"structured":[142],"linguistic":[143,174],"representations.":[144],"cross-modal":[146],"translation":[147],"mechanism":[148,215],"leverages":[149,168],"invariant":[151],"properties":[153],"mitigate":[158],"shifts":[160],"while":[161],"preserving":[162],"task-critical":[163],"hierarchies.":[165],"Our":[166,189],"capacity":[172],"structures":[175],"enhance":[177],"cross-domain":[178],"generalization,":[179],"effectively":[180],"bridging":[181],"visual-semantic":[183],"gap":[184],"unsupervised":[186],"adaptation":[187,207],"scenarios.":[188],"comprises":[191],"three":[192,228],"core":[193],"components:":[194],"1)":[195],"text":[196,202,217],"classification":[197],"branch":[198,208],"translating":[199],"images":[200],"prediction;":[204],"2)":[205],"image":[206],"supplementing":[209],"details;":[211],"3)":[213],"ensemble":[214],"reconciling":[216],"granularity":[221],"through":[222],"mismatch":[223],"detection.":[224],"Extensive":[225],"experiments":[226],"on":[227],"benchmark":[229],"datasets":[230],"validate":[231],"effectiveness":[233],"model,":[236],"achieving":[237],"state-of-the-art":[238],"performance.":[239]},"counts_by_year":[],"updated_date":"2026-04-23T06:14:38.165362","created_date":"2026-04-18T00:00:00"}