{"id":"https://openalex.org/W7133295703","doi":"https://doi.org/10.1016/j.displa.2026.103420","title":"Retrieval Augmented video captioning with quality-aware re-ranking and cross-gating fusion","display_name":"Retrieval Augmented video captioning with quality-aware re-ranking and cross-gating fusion","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133295703","doi":"https://doi.org/10.1016/j.displa.2026.103420"},"language":"en","primary_location":{"id":"doi:10.1016/j.displa.2026.103420","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.displa.2026.103420","pdf_url":null,"source":{"id":"https://openalex.org/S191329154","display_name":"Displays","issn_l":"0141-9382","issn":["0141-9382","1872-7387"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Displays","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/A5085542141","display_name":"Chengyang Fang","orcid":"https://orcid.org/0000-0002-3583-9119"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]},{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN","MY"],"is_corresponding":false,"raw_author_name":"Chengyang Fang","raw_affiliation_strings":["Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, China","School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, China","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127977688","display_name":"Jian Li (41607)","orcid":null},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128016625","display_name":"Yilong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilong Xie","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128026658","display_name":"Wenhui Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]},{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN","MY"],"is_corresponding":true,"raw_author_name":"Wenhui Jiang","raw_affiliation_strings":["Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, China","School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, China","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046229717","display_name":"Gangyan Zeng","orcid":"https://orcid.org/0000-0003-2696-8549"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangyan Zeng","raw_affiliation_strings":["School of Cyber Science and Engineering, Nanjing University of Science and Technology, Jiangsu, 210000, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Nanjing University of Science and Technology, Jiangsu, 210000, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016258860","display_name":"Z.H. Li","orcid":"https://orcid.org/0000-0002-2558-508X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixuan Li","raw_affiliation_strings":["Beijing Deeperception Technology Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"Beijing Deeperception Technology Co., Ltd., China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120882373","display_name":"Yuming Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]},{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN","MY"],"is_corresponding":true,"raw_author_name":"Yuming Fang","raw_affiliation_strings":["Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, China","School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, China","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Jiangxi, 330000, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5120882373","https://openalex.org/A5128026658"],"corresponding_institution_ids":["https://openalex.org/I173029219","https://openalex.org/I59649739"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51601518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"93","issue":null,"first_page":"103420","last_page":"103420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9807999730110168,"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":0.9807999730110168,"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":0.00860000029206276,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.002099999925121665,"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":0.9815999865531921},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5335000157356262},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46810001134872437},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44620001316070557},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.31869998574256897},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2919999957084656},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.29030001163482666}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9815999865531921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840499997138977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5458999872207642},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44620001316070557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.displa.2026.103420","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.displa.2026.103420","pdf_url":null,"source":{"id":"https://openalex.org/S191329154","display_name":"Displays","issn_l":"0141-9382","issn":["0141-9382","1872-7387"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Displays","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F3692415409","display_name":"Double Thousand Plan of Jiangxi Province","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null},{"id":"https://openalex.org/F4320327780","display_name":"Key Research and Development Program of Jiangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3134875898","https://openalex.org/W4281560470","https://openalex.org/W4387385612","https://openalex.org/W4387934928","https://openalex.org/W4390075233","https://openalex.org/W4404562753","https://openalex.org/W4407449399","https://openalex.org/W4412530017"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-03-04T00:00:00"}
