{"id":"https://openalex.org/W4399072500","doi":"https://doi.org/10.1007/s11760-024-03268-0","title":"Research on image caption generation method based on multi-modal pre-training model and text mixup optimization","display_name":"Research on image caption generation method based on multi-modal pre-training model and text mixup optimization","publication_year":2024,"publication_date":"2024-05-28","ids":{"openalex":"https://openalex.org/W4399072500","doi":"https://doi.org/10.1007/s11760-024-03268-0"},"language":"en","primary_location":{"id":"doi:10.1007/s11760-024-03268-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11760-024-03268-0","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/A5056684326","display_name":"Jing-Tao Sun","orcid":"https://orcid.org/0000-0002-8837-7405"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing-Tao Sun","raw_affiliation_strings":["School of Computer Science and Technology, Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shaanxi, China","Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shaanxi, China","institution_ids":["https://openalex.org/I4210136859"]},{"raw_affiliation_string":"Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shaanxi, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101367667","display_name":"Xuan Min","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuan Min","raw_affiliation_strings":["School of Computer Science and Technology, Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shaanxi, China","Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shaanxi, China","institution_ids":["https://openalex.org/I4210136859"]},{"raw_affiliation_string":"Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi\u2019an University of Posts and Telecommunications, Xi\u2019an, 710121, Shaanxi, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101367667"],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":{"value":3190,"currency":"USD","value_usd":3190},"apc_paid":null,"fwci":0.1527,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40491764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":94},"biblio":{"volume":"18","issue":"8-9","first_page":"5743","last_page":"5761"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9930999875068665,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.7411434054374695},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7328206300735474},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5719272494316101},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4663360118865967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.450484037399292},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4267027676105499},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41092780232429504},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0645211935043335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411434054374695},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7328206300735474},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5719272494316101},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4663360118865967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.450484037399292},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4267027676105499},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41092780232429504},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0645211935043335},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"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:10.1007/s11760-024-03268-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11760-024-03268-0","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":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2137918516","https://openalex.org/W2510520237","https://openalex.org/W2550553598","https://openalex.org/W2558834163","https://openalex.org/W2588822708","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2945260553","https://openalex.org/W2950813464","https://openalex.org/W2962835968","https://openalex.org/W2963084599","https://openalex.org/W2963187678","https://openalex.org/W2966715458","https://openalex.org/W2974497444","https://openalex.org/W2979924880","https://openalex.org/W2986670728","https://openalex.org/W3035542229","https://openalex.org/W3046675509","https://openalex.org/W3100245404","https://openalex.org/W3115242847","https://openalex.org/W3124043039","https://openalex.org/W3135367836","https://openalex.org/W3143320354","https://openalex.org/W3167939936","https://openalex.org/W3173220247","https://openalex.org/W3174311454","https://openalex.org/W3176417455","https://openalex.org/W3193402170","https://openalex.org/W4221147537","https://openalex.org/W4226182655","https://openalex.org/W4237129069","https://openalex.org/W4312922092","https://openalex.org/W4313131769","https://openalex.org/W6607045254","https://openalex.org/W6745136726","https://openalex.org/W6778883912","https://openalex.org/W6789705400"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
