{"id":"https://openalex.org/W4415353920","doi":"https://doi.org/10.1007/s00371-026-04509-8","title":"RGFRCap: enhancing image captioning with retrieval-guided semantic feature refinement","display_name":"RGFRCap: enhancing image captioning with retrieval-guided semantic feature refinement","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W4415353920","doi":"https://doi.org/10.1007/s00371-026-04509-8"},"language":"en","primary_location":{"id":"doi:10.1007/s00371-026-04509-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00371-026-04509-8","pdf_url":null,"source":{"id":"https://openalex.org/S73060445","display_name":"The Visual Computer","issn_l":"0178-2789","issn":["0178-2789","1432-2315"],"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":"The Visual Computer","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-7721105/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101658712","display_name":"Jiaqi Fan","orcid":"https://orcid.org/0000-0002-2642-2485"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Fan","raw_affiliation_strings":["Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, No. 4800 Cao\u2019an Road, Shanghai, 201804, Shanghai, China","Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, No. 4800 Cao\u2019an Road, Shanghai, 201804, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063286550","display_name":"Hongqing Chu","orcid":"https://orcid.org/0000-0002-8015-9788"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongqing Chu","raw_affiliation_strings":["School of Automotive Studies, Tongji University, No. 4800 Cao\u2019an Road, Shanghai, 201804, Shanghai, China","Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, No. 4800 Cao\u2019an Road, Shanghai, 201804, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Fang","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Zhongguancun South Street, Beijing, 100081, Beijing, China","Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Zhongguancun South Street, Beijing, 100081, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012709709","display_name":"Jia Zhang","orcid":"https://orcid.org/0000-0002-2513-4115"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zhang","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Zhongguancun South Street, Beijing, 100081, Beijing, China","Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Zhongguancun South Street, Beijing, 100081, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053095481","display_name":"Quanbo Ge","orcid":"https://orcid.org/0000-0002-0044-6059"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanbo Ge","raw_affiliation_strings":["School of Automation, Nanjing University of Information Science and Technology, No. 219 Ningliu Road, Nanjing, 210044, Jiangsu, China","Nanjing University of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Nanjing University of Information Science and Technology, No. 219 Ningliu Road, Nanjing, 210044, Jiangsu, China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"Nanjing University of Information Science and Technology","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064212745","display_name":"Bingzhao Gao","orcid":"https://orcid.org/0000-0001-5155-7835"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bingzhao Gao","raw_affiliation_strings":["School of Automotive Studies, Tongji University, No. 4800 Cao\u2019an Road, Shanghai, 201804, Shanghai, China","Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, No. 4800 Cao\u2019an Road, Shanghai, 201804, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064212745"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01363149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"8","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":0.9998000264167786,"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":0.9998000264167786,"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":0.9534000158309937,"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":0.9282000064849854,"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/closed-captioning","display_name":"Closed captioning","score":0.8970999717712402},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5636000037193298},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.46939998865127563},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.45399999618530273},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.3946000039577484},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3871999979019165},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37860000133514404}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8970999717712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5968000292778015},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4571000039577484},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.45399999618530273},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.3946000039577484},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26249998807907104}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00371-026-04509-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00371-026-04509-8","pdf_url":null,"source":{"id":"https://openalex.org/S73060445","display_name":"The Visual Computer","issn_l":"0178-2789","issn":["0178-2789","1432-2315"],"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":"The Visual Computer","raw_type":"journal-article"},{"id":"doi:10.21203/rs.3.rs-7721105/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-7721105/v1","pdf_url":"https://www.researchsquare.com/article/rs-7721105/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-7721105/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-7721105/v1","pdf_url":"https://www.researchsquare.com/article/rs-7721105/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1163267705","display_name":null,"funder_award_id":"62273256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4606321376","display_name":null,"funder_award_id":"2021SHZDZX0100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8111733239","display_name":null,"funder_award_id":"2021SHZDZX0100","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415353920.pdf","grobid_xml":"https://content.openalex.org/works/W4415353920.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-21T00:00:00"}
