{"id":"https://openalex.org/W4407825355","doi":"https://doi.org/10.1007/s11760-025-03871-9","title":"CDZL: a controllable diversity zero-shot image caption model using large language models","display_name":"CDZL: a controllable diversity zero-shot image caption model using large language models","publication_year":2025,"publication_date":"2025-02-21","ids":{"openalex":"https://openalex.org/W4407825355","doi":"https://doi.org/10.1007/s11760-025-03871-9"},"language":"en","primary_location":{"id":"doi:10.1007/s11760-025-03871-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11760-025-03871-9","pdf_url":null,"source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","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/A5016994227","display_name":"Xin Zhao","orcid":"https://orcid.org/0009-0000-2561-8729"},"institutions":[{"id":"https://openalex.org/I4210124148","display_name":"Microbiology Institute of Shaanxi","ror":"https://ror.org/02wt4jg41","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124148"]},{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Zhao","raw_affiliation_strings":["Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210124148"]},{"raw_affiliation_string":"Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757104","display_name":"Weiwei Kong","orcid":"https://orcid.org/0000-0002-5013-3739"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]},{"id":"https://openalex.org/I4210124148","display_name":"Microbiology Institute of Shaanxi","ror":"https://ror.org/02wt4jg41","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124148"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Kong","raw_affiliation_strings":["Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210124148"]},{"raw_affiliation_string":"Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089297052","display_name":"Zongyao Liu","orcid":"https://orcid.org/0000-0003-4482-9657"},"institutions":[{"id":"https://openalex.org/I4210124148","display_name":"Microbiology Institute of Shaanxi","ror":"https://ror.org/02wt4jg41","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124148"]},{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongyao Liu","raw_affiliation_strings":["Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210124148"]},{"raw_affiliation_string":"Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586260","display_name":"Menghao Wang","orcid":"https://orcid.org/0000-0002-8972-8588"},"institutions":[{"id":"https://openalex.org/I4210124148","display_name":"Microbiology Institute of Shaanxi","ror":"https://ror.org/02wt4jg41","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124148"]},{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghao Wang","raw_affiliation_strings":["Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210124148"]},{"raw_affiliation_string":"Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367690","display_name":"Yiwen Li","orcid":"https://orcid.org/0000-0002-6874-0350"},"institutions":[{"id":"https://openalex.org/I4210124148","display_name":"Microbiology Institute of Shaanxi","ror":"https://ror.org/02wt4jg41","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124148"]},{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Li","raw_affiliation_strings":["Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210124148"]},{"raw_affiliation_string":"Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shannxi, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016994227"],"corresponding_institution_ids":["https://openalex.org/I4210124148","https://openalex.org/I4210136859"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":2.7335,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88516525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"19","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9821000099182129,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9797000288963318,"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/zero","display_name":"Zero (linguistics)","score":0.7411984801292419},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6861474514007568},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.6481932401657104},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6240136623382568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49123185873031616},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38453176617622375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3747958540916443},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3665674030780792},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3331514298915863},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28449252247810364},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09980010986328125},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.09252700209617615},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08779740333557129}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7411984801292419},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6861474514007568},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.6481932401657104},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6240136623382568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49123185873031616},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38453176617622375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3747958540916443},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3665674030780792},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3331514298915863},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28449252247810364},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09980010986328125},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.09252700209617615},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08779740333557129},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11760-025-03871-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11760-025-03871-9","pdf_url":null,"source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2506483933","https://openalex.org/W2788277448","https://openalex.org/W2901433466","https://openalex.org/W2997248215","https://openalex.org/W3008585839","https://openalex.org/W3185341429","https://openalex.org/W4312289196","https://openalex.org/W4313131769","https://openalex.org/W4386075661","https://openalex.org/W4390873015"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}
