{"id":"https://openalex.org/W4403182929","doi":"https://doi.org/10.1109/tnnls.2024.3440872","title":"Variational Transformer: A Framework Beyond the Tradeoff Between Accuracy and Diversity for Image Captioning","display_name":"Variational Transformer: A Framework Beyond the Tradeoff Between Accuracy and Diversity for Image Captioning","publication_year":2024,"publication_date":"2024-10-07","ids":{"openalex":"https://openalex.org/W4403182929","doi":"https://doi.org/10.1109/tnnls.2024.3440872","pmid":"https://pubmed.ncbi.nlm.nih.gov/39374280"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3440872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3440872","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5085584344","display_name":"Longzhen Yang","orcid":"https://orcid.org/0000-0002-5791-145X"},"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":"Longzhen Yang","raw_affiliation_strings":["Department of Electronic and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091130234","display_name":"Lianghua He","orcid":"https://orcid.org/0000-0002-5250-170X"},"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":"Lianghua He","raw_affiliation_strings":["Department of Electronic and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084461937","display_name":"Die Hu","orcid":"https://orcid.org/0000-0001-8081-8512"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Die Hu","raw_affiliation_strings":["Department of Communication Science and Engineering, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Communication Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101847419","display_name":"Yihang Liu","orcid":"https://orcid.org/0000-0003-4257-2528"},"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":"Yihang Liu","raw_affiliation_strings":["Department of Electronic and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057399853","display_name":"Yitao Peng","orcid":"https://orcid.org/0000-0002-2680-5822"},"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":"Yitao Peng","raw_affiliation_strings":["Department of Electronic and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022661905","display_name":"Hongzhou Chen","orcid":"https://orcid.org/0000-0002-8310-3202"},"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":"Hongzhou Chen","raw_affiliation_strings":["Department of Electronic and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081318069","display_name":"MengChu Zhou","orcid":"https://orcid.org/0000-0002-5408-8752"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"MengChu Zhou","raw_affiliation_strings":["School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5085584344"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":1.2464,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81246636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"36","issue":"5","first_page":"9500","last_page":"9511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9865000247955322,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9814000129699707,"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":0.8761340379714966},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6642693877220154},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45917701721191406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44410139322280884},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.44143596291542053},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.308804452419281},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.23958155512809753},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.21116763353347778},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16553422808647156},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07612401247024536}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8761340379714966},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6642693877220154},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45917701721191406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44410139322280884},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.44143596291542053},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.308804452419281},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.23958155512809753},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.21116763353347778},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16553422808647156},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07612401247024536},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3440872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3440872","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:39374280","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39374280","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7355213507","display_name":null,"funder_award_id":"62171323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2033178790","https://openalex.org/W2099111195","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2149557440","https://openalex.org/W2506483933","https://openalex.org/W2604178507","https://openalex.org/W2745461083","https://openalex.org/W2954841306","https://openalex.org/W2962735233","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963448089","https://openalex.org/W2986670728","https://openalex.org/W3015284505","https://openalex.org/W3034655362","https://openalex.org/W3034984754","https://openalex.org/W3091588028","https://openalex.org/W3110042533","https://openalex.org/W3175824375","https://openalex.org/W3196122027","https://openalex.org/W3203247740","https://openalex.org/W3207942052","https://openalex.org/W4312922092","https://openalex.org/W4385245566","https://openalex.org/W4386566667","https://openalex.org/W4402215325","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6678470764","https://openalex.org/W6682631176","https://openalex.org/W6685322675","https://openalex.org/W6687045409","https://openalex.org/W6728274705","https://openalex.org/W6744104549","https://openalex.org/W6744627333","https://openalex.org/W6767459567","https://openalex.org/W6773707559","https://openalex.org/W6774950721","https://openalex.org/W6775684168","https://openalex.org/W6780593937","https://openalex.org/W6800139874","https://openalex.org/W6811013733","https://openalex.org/W6839015040","https://openalex.org/W6849177959"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"Accuracy":[0],"and":[1,14,35,80,95,144,150],"diversity":[2,61,145],"represent":[3],"two":[4],"critical":[5],"quantifiable":[6],"performance":[7,161],"metrics":[8],"in":[9,98,142,169],"the":[10,27,32,46,107,125,154,164,178,184],"generation":[11],"of":[12,25,119,175,181],"natural":[13],"semantically":[15],"accurate":[16],"captions.":[17,58],"While":[18],"efforts":[19],"are":[20,54],"made":[21],"to":[22,31,90,148,166],"enhance":[23],"one":[24],"them,":[26],"other":[28],"suffers":[29],"due":[30],"inherent":[33],"conflicting":[34],"complex":[36],"relationship":[37],"between":[38],"them.":[39],"In":[40],"this":[41],"study,":[42],"we":[43,66,86,114],"demonstrate":[44],"that":[45,136,162],"suboptimal":[47],"accuracy":[48,143],"levels":[49],"derived":[50],"from":[51],"human":[52,167,179],"annotations":[53,168],"unsuitable":[55],"for":[56],"machine-generated":[57],"To":[59],"boost":[60],"while":[62],"maintaining":[63],"high":[64,103],"accuracy,":[65],"propose":[67],"an":[68],"innovative":[69],"variational":[70],"transformer":[71],"(VaT)":[72],"framework.":[73],"By":[74,105],"integrating":[75],"\"invisible":[76],"information":[77,94],"prior":[78],"(IIP)\"":[79],"\"auto-selectable":[81],"Gaussian":[82],"mixture":[83],"model":[84],"(AGMM),\"":[85],"enable":[87],"its":[88,160,173],"encoder":[89],"learn":[91],"precise":[92],"linguistic":[93],"object":[96],"relationships":[97],"various":[99],"scenes,":[100],"thus":[101],"ensuring":[102],"accuracy.":[104],"incorporating":[106],"\"range-median":[108],"reward":[109],"(RMR)\"":[110],"baseline":[111],"into":[112,190],"it,":[113],"preserve":[115],"a":[116],"wider":[117],"range":[118],"candidates":[120],"with":[121,172],"higher":[122],"rewards":[123],"during":[124],"reinforcement-learning-based":[126],"training":[127],"process,":[128],"thereby":[129],"guaranteeing":[130],"outstanding":[131],"diversity.":[132],"Experimental":[133],"results":[134],"indicate":[135],"our":[137,157],"method":[138,185],"achieves":[139],"simultaneous":[140],"improvements":[141],"by":[146],"up":[147],"1.1%":[149],"4.8%,":[151],"respectively,":[152],"over":[153],"state-of-the-art.":[155],"Furthermore,":[156],"approach":[158],"demonstrates":[159],"is":[163],"closest":[165],"semantic":[170],"retrieval,":[171],"score":[174,180],"50.3":[176],"versus":[177],"50.6.":[182],"Thus,":[183],"can":[186],"be":[187],"readily":[188],"put":[189],"industrial":[191],"use.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}