{"id":"https://openalex.org/W4409916728","doi":"https://doi.org/10.1109/access.2025.3565682","title":"Research on Digital Media Art for Image Caption Generation Based on Integrated Transformer Models in CLIP","display_name":"Research on Digital Media Art for Image Caption Generation Based on Integrated Transformer Models in CLIP","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409916728","doi":"https://doi.org/10.1109/access.2025.3565682"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3565682","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3565682","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3565682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084245098","display_name":"Lu Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I207528943","display_name":"Chengdu Medical College","ror":"https://ror.org/01c4jmp52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I207528943"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Gao","raw_affiliation_strings":["School of Art Design and Creativity, Chengdu Textile College, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0000-2243-2822","affiliations":[{"raw_affiliation_string":"School of Art Design and Creativity, Chengdu Textile College, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I207528943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016712271","display_name":"Xinlei Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106931","display_name":"Jiaxing Vocational Technical College","ror":"https://ror.org/02cydx698","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210106931"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Pang","raw_affiliation_strings":["School of Information Engineering, Bingtuan Xingxin Vocational and Technical College, Tiemenguan City, China","School of Information Engineering, Bingtuan Xingxin Vocational and Technical College, Tiemenguan, China"],"raw_orcid":"https://orcid.org/0009-0002-8850-4352","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Bingtuan Xingxin Vocational and Technical College, Tiemenguan City, China","institution_ids":["https://openalex.org/I4210106931"]},{"raw_affiliation_string":"School of Information Engineering, Bingtuan Xingxin Vocational and Technical College, Tiemenguan, China","institution_ids":["https://openalex.org/I4210106931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":6.2166,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93653154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"75894","last_page":"75910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9402999877929688,"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/T14254","display_name":"Digital Media and Visual Art","score":0.9358999729156494,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.7155426144599915},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5843870043754578},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42028263211250305},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4200844466686249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3262184262275696},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13775241374969482},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11223182082176208},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06928330659866333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7155426144599915},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5843870043754578},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42028263211250305},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4200844466686249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3262184262275696},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13775241374969482},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11223182082176208},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06928330659866333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3565682","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3565682","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:024be486ed944325ba1fb219baf91fa8","is_oa":true,"landing_page_url":"https://doaj.org/article/024be486ed944325ba1fb219baf91fa8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 75894-75910 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3565682","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3565682","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1895577753","https://openalex.org/W1987835821","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2133459682","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2508429489","https://openalex.org/W2555182955","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2901988662","https://openalex.org/W2963758027","https://openalex.org/W2986670728","https://openalex.org/W2998356391","https://openalex.org/W3000494761","https://openalex.org/W3034655362","https://openalex.org/W3204358542","https://openalex.org/W4281686064","https://openalex.org/W4313890505","https://openalex.org/W4319777846","https://openalex.org/W4321193249","https://openalex.org/W4379115721","https://openalex.org/W4387096088","https://openalex.org/W4390195594","https://openalex.org/W4392355597","https://openalex.org/W4396681760","https://openalex.org/W6763643401","https://openalex.org/W6775684168","https://openalex.org/W6779564468","https://openalex.org/W6791353385","https://openalex.org/W6801823939","https://openalex.org/W6803567076"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Digital":[0],"media":[1,16],"art":[2,17],"has":[3,101],"a":[4,60,112,143],"wide":[5],"application":[6],"in":[7,158],"the":[8,42,64,92,97,119,133,165,186,197,205,213,221,232,235],"field":[9,93],"of":[10,31,68,94,136,199,234],"image":[11,25,109],"caption":[12],"generation.":[13],"In":[14,91,129],"digital":[15],"exhibitions":[18],"or":[19,33],"online":[20],"works":[21,26],"displays,":[22],"some":[23],"complex":[24],"may":[27],"have":[28,227],"multiple":[29],"layers":[30],"meanings":[32],"abstract":[34],"expressions,":[35],"which":[36,106,150,171],"can":[37,45],"help":[38],"viewers":[39],"better":[40],"understand":[41],"works.":[43],"It":[44],"also":[46,102,239],"serve":[47],"as":[48],"another":[49],"auxiliary":[50],"element":[51],"besides":[52],"sound,":[53],"collaborating":[54],"with":[55],"visual":[56],"elements":[57],"to":[58,72,78,87,131,195,210],"provide":[59,73],"richer":[61],"experience":[62],"for":[63,121,188],"audience.":[65],"The":[66,81],"purpose":[67],"picture":[69,95],"captioning":[70],"is":[71,84],"textual":[74],"descriptions":[75],"that":[76,225],"correlate":[77],"input":[79],"images.":[80],"CLIP":[82,168],"paradigm":[83],"highly":[85],"versatile":[86],"resolve":[88],"vision-text":[89],"difficulties.":[90,128],"description,":[96],"standard":[98],"Transformer":[99,166],"architecture":[100],"exhibited":[103],"good":[104],"effects,":[105],"uses":[107],"an":[108],"encoder":[110],"and":[111,118,155,175,191,247],"text":[113],"decoder.":[114],"Large":[115],"parameter":[116,153,173],"numbers":[117],"demand":[120],"further":[122,211],"data":[123],"preprocessing":[124],"are":[125],"still":[126],"significant":[127],"order":[130],"replace":[132],"fundamental":[134],"features":[135],"conventional":[137],"multi-modal":[138],"fusion":[139],"models,":[140],"we":[141,163,184,203,226],"propose":[142,164],"New":[144],"Multi-modal":[145],"Fusion":[146,167],"Attention":[147],"module":[148],"(NMFA),":[149],"efficiently":[151],"decreases":[152],"sizes":[154,174],"computational":[156],"complexity":[157],"half.":[159],"Expanding":[160],"upon":[161],"this,":[162],"(TFC)":[169],"model,":[170],"minimizes":[172],"processing":[176],"demands":[177],"while":[178],"getting":[179],"remarkable":[180],"assessment":[181],"scores.":[182],"Additionally,":[183],"strengthen":[185],"mechanism":[187],"cumulative":[189],"points":[190],"reward":[192],"sequence":[193],"length":[194],"encourage":[196],"construction":[198],"larger":[200],"sequences.":[201],"Finally,":[202],"combine":[204],"enhanced":[206],"beam":[207],"search":[208],"technique":[209],"train":[212],"TFC":[214,236],"model.":[215],"Results":[216],"from":[217],"our":[218],"testing":[219],"on":[220],"MSCOCO":[222],"dataset":[223],"reveal":[224],"not":[228],"only":[229],"greatly":[230],"improved":[231],"efficiency":[233],"model":[237,249],"but":[238],"speeded":[240],"up":[241],"its":[242],"runtime":[243],"by":[244,251],"eight":[245],"times":[246],"reduced":[248],"parameters":[250],"over":[252],"50%.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}