{"id":"https://openalex.org/W4407156489","doi":"https://doi.org/10.1145/3715699","title":"Unified Text-Image Space Alignment with Cross-Modal Prompting in CLIP for UDA","display_name":"Unified Text-Image Space Alignment with Cross-Modal Prompting in CLIP for UDA","publication_year":2025,"publication_date":"2025-02-05","ids":{"openalex":"https://openalex.org/W4407156489","doi":"https://doi.org/10.1145/3715699"},"language":"en","primary_location":{"id":"doi:10.1145/3715699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3715699","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5031056278","display_name":"Yifan Jiao","orcid":"https://orcid.org/0000-0002-8923-6997"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Jiao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China","School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-8923-6997","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089417191","display_name":"Chenglong Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Cai","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China","School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0009-6756-2079","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China","School of Computer Science, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":7.6197,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96587104,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"21","issue":"3","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.991599977016449,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.991599977016449,"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/T10028","display_name":"Topic Modeling","score":0.9907000064849854,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.8739109039306641},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6356978416442871},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5258484482765198},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5086408853530884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44765931367874146},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4471893906593323},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4190409481525421},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3936852514743805},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1059243381023407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8739109039306641},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6356978416442871},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5258484482765198},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5086408853530884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44765931367874146},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4471893906593323},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4190409481525421},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3936852514743805},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1059243381023407},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3715699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3715699","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1972370969","https://openalex.org/W2031342017","https://openalex.org/W2104094955","https://openalex.org/W2108598243","https://openalex.org/W2165698076","https://openalex.org/W2194775991","https://openalex.org/W2584886900","https://openalex.org/W2627183927","https://openalex.org/W2750779823","https://openalex.org/W2911495555","https://openalex.org/W2970476646","https://openalex.org/W2978573218","https://openalex.org/W2981720610","https://openalex.org/W3033696290","https://openalex.org/W3035519852","https://openalex.org/W3039883906","https://openalex.org/W3044438666","https://openalex.org/W3096437212","https://openalex.org/W3102758664","https://openalex.org/W3125003080","https://openalex.org/W3152956381","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W4205807230","https://openalex.org/W4205991051","https://openalex.org/W4206967050","https://openalex.org/W4285605356","https://openalex.org/W4300979120","https://openalex.org/W4307975143","https://openalex.org/W4312792979","https://openalex.org/W4386076502","https://openalex.org/W4388543952","https://openalex.org/W4390190228","https://openalex.org/W4392172801","https://openalex.org/W4394627552","https://openalex.org/W6739901393","https://openalex.org/W6811219898"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399","https://openalex.org/W2383812217","https://openalex.org/W2326515389","https://openalex.org/W2491005386"],"abstract_inverted_index":{"Unsupervised":[0],"Domain":[1],"Adaptation":[2],"(UDA)":[3],"aims":[4],"to":[5,14,20,41,59,124,137,160,183,212],"transfer":[6],"models":[7],"trained":[8],"on":[9,65,230,237,240,244],"a":[10,86,103,118,153,203],"labeled":[11],"source":[12,50],"domain":[13,163,167,176,211],"an":[15],"unlabeled":[16],"target":[17,52,95,210],"domain.":[18,96],"Due":[19],"the":[21,66,94,134,146,170,180,186,209,214,219,227],"excellent":[22],"generalization":[23,217],"ability":[24],"of":[25,68,148,188,218],"Vision":[26],"Language":[27],"Models":[28],"(VLMs)":[29],"such":[30],"as":[31],"CLIP":[32,40],"in":[33,80,89,93],"downstream":[34],"tasks,":[35],"most":[36],"recent":[37],"methods":[38,57],"apply":[39],"UDA":[42,233],"tasks":[43],"through":[44],"learning":[45],"domain-specific":[46,77,126,139,197],"text":[47,78,198],"prompts":[48,79,128,132],"for":[49,113,133,165,208],"and":[51,129,142,168,216,242],"domains":[53],"separately.":[54],"However,":[55],"these":[56,174],"fail":[58],"dynamically":[60],"adjust":[61],"image":[62,127,131,149,171,181],"features":[63,164,172,182],"based":[64],"characteristics":[67,187],"their":[69,74,189,194],"respective":[70,190],"domains,":[71,191],"thereby":[72,192],"limiting":[73],"alignment":[75,195],"with":[76,108,173,196],"CLIP\u2019s":[81],"joint":[82],"space,":[83],"which":[84,178],"is":[85],"key":[87],"factor":[88],"improving":[90],"classification":[91],"performance":[92,229],"To":[97],"bridge":[98],"this":[99],"gap,":[100],"we":[101,116,151,201],"propose":[102],"Unified":[104],"Text-Image":[105],"Space":[106],"Alignment":[107],"Cross-Modal":[109,119],"Prompting":[110],"(UTISA)":[111],"framework":[112],"UDA.":[114],"First,":[115],"introduce":[117,152,202],"Prompt":[120],"Learning":[121],"(CMP)":[122],"module":[123,159],"generate":[125],"layer-specific":[130],"visual":[135],"branch":[136],"encode":[138],"knowledge":[140],"globally":[141],"locally.":[143],"Second,":[144],"under":[145],"guidance":[147],"prompts,":[150],"Domain-Aware":[154],"Multi-Layer":[155],"Feature":[156],"Fusion":[157],"(DMF)":[158],"construct":[161],"multi-layer":[162,175],"each":[166],"enhance":[169,213],"features,":[177],"enables":[179],"better":[184],"reflect":[185],"promoting":[193],"prompts.":[199],"Moreover,":[200],"Perturbation-Driven":[204],"Regularization":[205],"(PDR)":[206],"mechanism":[207],"robustness":[215],"model.":[220],"The":[221],"experiments":[222],"demonstrate":[223],"that":[224],"UTISA":[225],"achieves":[226],"best":[228],"three":[231],"mainstream":[232],"benchmarks,":[234],"including":[235],"87.9%":[236],"Office-Home,":[238],"90.9%":[239],"VisDA-2017,":[241],"62.4%":[243],"DomainNet.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}