{"id":"https://openalex.org/W4389947181","doi":"https://doi.org/10.3233/jifs-233004","title":"RVAIC: Refined visual attention for improved image captioning","display_name":"RVAIC: Refined visual attention for improved image captioning","publication_year":2023,"publication_date":"2023-12-19","ids":{"openalex":"https://openalex.org/W4389947181","doi":"https://doi.org/10.3233/jifs-233004"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-233004","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-233004","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","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/A5067972997","display_name":"Majjed Al-Qatf","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["CN","IE"],"is_corresponding":false,"raw_author_name":"Majjed Al-Qatf","raw_affiliation_strings":["Insight Centre for Data Analytics, University of Galway, Galway, Ireland","School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, University of Galway, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089032960","display_name":"Ammar Hawbani","orcid":"https://orcid.org/0000-0002-1069-3993"},"institutions":[{"id":"https://openalex.org/I125904092","display_name":"Shenyang Aerospace University","ror":"https://ror.org/02423gm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I125904092"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ammar Hawbani","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","School of Computer Science, Shenyang Aerospace University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Computer Science, Shenyang Aerospace University, Shenyang, China","institution_ids":["https://openalex.org/I125904092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742230","display_name":"Xingfu Wang","orcid":"https://orcid.org/0000-0002-1301-3535"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"XingFu Wang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109671635","display_name":"Amr Abdusallam","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Amr Abdusallam","raw_affiliation_strings":["School of Electronic Engineering and Information Science, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Information Science, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012786887","display_name":"Saeed Hamood Alsamhi","orcid":"https://orcid.org/0000-0003-2857-6979"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]},{"id":"https://openalex.org/I78137547","display_name":"Ibb University","ror":"https://ror.org/00fhcxc56","country_code":"YE","type":"education","lineage":["https://openalex.org/I78137547"]}],"countries":["IE","YE"],"is_corresponding":false,"raw_author_name":"Saeed Alsamhi","raw_affiliation_strings":["Faculty of Engineering, IBB University, IBB, Yemen","Insight Centre for Data Analytics, University of Galway, Galway, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, IBB University, IBB, Yemen","institution_ids":["https://openalex.org/I78137547"]},{"raw_affiliation_string":"Insight Centre for Data Analytics, University of Galway, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064710846","display_name":"Mohammed Al\u2010Habib","orcid":"https://orcid.org/0000-0003-3651-4954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed Alhabib","raw_affiliation_strings":["School of Computer Science and Engineering, Centeral South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Centeral South University, Changsha, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027850521","display_name":"Edward Curry","orcid":"https://orcid.org/0000-0001-8236-6433"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Edward Curry","raw_affiliation_strings":["Insight Centre for Data Analytics, University of Galway, Galway, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, University of Galway, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089032960","https://openalex.org/A5100742230"],"corresponding_institution_ids":["https://openalex.org/I125904092","https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.2763,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82730124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"46","issue":"2","first_page":"3447","last_page":"3459"},"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":0.9977999925613403,"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":0.9955000281333923,"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":0.9408532381057739},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.9031751751899719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8596123456954956},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6379112601280212},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6305078268051147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6189286708831787},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5991958975791931},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5773159265518188},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4234277606010437},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.4230073392391205},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4101581275463104},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3729903995990753},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.14712971448898315},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1366630494594574}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9408532381057739},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9031751751899719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8596123456954956},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6379112601280212},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6305078268051147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6189286708831787},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5991958975791931},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5773159265518188},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4234277606010437},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.4230073392391205},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4101581275463104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3729903995990753},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.14712971448898315},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1366630494594574},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-233004","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-233004","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2463955103","https://openalex.org/W2962938439","https://openalex.org/W2965922392","https://openalex.org/W2987327987","https://openalex.org/W2997003477","https://openalex.org/W2997279317","https://openalex.org/W3010997078","https://openalex.org/W3045147787","https://openalex.org/W3119689583","https://openalex.org/W3131872037","https://openalex.org/W3136792391","https://openalex.org/W4293731196"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4285326772","https://openalex.org/W4376118624","https://openalex.org/W3080832216","https://openalex.org/W4389279194","https://openalex.org/W3170224572","https://openalex.org/W3043103998"],"abstract_inverted_index":{"Visual":[0],"attention":[1,44,74,81,144],"has":[2],"emerged":[3],"as":[4,15],"a":[5,56,71,98,113,118],"prominent":[6],"approach":[7],"for":[8,106],"improving":[9],"the":[10,18,25,30,35,46,48,84,94,107,123,128,134,156],"effectiveness":[11,153],"of":[12,37,52,87,160],"image":[13,31,148,161],"captioning,":[14],"it":[16],"enables":[17],"decoder":[19],"network":[20],"to":[21,102,116,121],"focus":[22],"selectively":[23],"on":[24,59,133],"most":[26],"salient":[27],"regions":[28],"in":[29,154],"content,":[32],"thereby":[33],"facilitating":[34],"generation":[36],"precise":[38],"and":[39,145,158],"informative":[40],"captions.":[41,162],"Although":[42],"visual":[43,73,80,108,143],"achieves":[45],"improvement,":[47],"small":[49],"numerical":[50],"values":[51],"its":[53,60,63,152],"input":[54,125],"have":[55],"negative":[57],"impact":[58],"softmax,":[61],"decreasing":[62],"effectiveness.":[64],"To":[65],"address":[66],"this":[67],"limitation,":[68],"we":[69,111],"propose":[70],"refined":[72],"(RVA)":[75],"framework":[76],"that":[77,139],"internally":[78],"reweights":[79],"by":[82,126],"leveraging":[83],"language":[85,95],"context":[86,96],"previously":[88],"generated":[89],"words.":[90],"We":[91],"first":[92],"feed":[93],"into":[97],"fully":[99],"connected":[100],"layer":[101],"obtain":[103,117],"appropriate":[104],"dimensions":[105],"features.":[109],"Then,":[110],"use":[112],"sigmoid":[114],"function":[115],"probability":[119],"distribution":[120],"reweight":[122],"softmax\u2019s":[124],"applying":[127],"multiplication":[129],"process.":[130],"Experiments":[131],"conducted":[132],"MS":[135],"COCO":[136],"dataset":[137],"demonstrate":[138],"RVA":[140],"outperforms":[141],"traditional":[142],"other":[146],"existing":[147],"captioning":[149],"methods,":[150],"highlighting":[151],"enhancing":[155],"accuracy":[157],"informativeness":[159]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
