{"id":"https://openalex.org/W4383263774","doi":"https://doi.org/10.1111/exsy.13392","title":"Enhanced transformer model for video caption generation","display_name":"Enhanced transformer model for video caption generation","publication_year":2023,"publication_date":"2023-07-05","ids":{"openalex":"https://openalex.org/W4383263774","doi":"https://doi.org/10.1111/exsy.13392"},"language":"en","primary_location":{"id":"doi:10.1111/exsy.13392","is_oa":true,"landing_page_url":"https://doi.org/10.1111/exsy.13392","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/exsy.13392","source":{"id":"https://openalex.org/S72232612","display_name":"Expert Systems","issn_l":"0266-4720","issn":["0266-4720","1468-0394"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/exsy.13392","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057229501","display_name":"Soumya Varma","orcid":"https://orcid.org/0000-0003-3037-4225"},"institutions":[{"id":"https://openalex.org/I119668213","display_name":"Karunya University","ror":"https://ror.org/03k23nv15","country_code":"IN","type":"education","lineage":["https://openalex.org/I119668213"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumya Varma","raw_affiliation_strings":["Department of CSE Karunya Institute of Technology and Sciences  Coimbatore India","Department of CSE, Karunya Institute of Technology and Sciences, Coimbatore, India"],"raw_orcid":"https://orcid.org/0000-0003-3037-4225","affiliations":[{"raw_affiliation_string":"Department of CSE Karunya Institute of Technology and Sciences  Coimbatore India","institution_ids":["https://openalex.org/I119668213"]},{"raw_affiliation_string":"Department of CSE, Karunya Institute of Technology and Sciences, Coimbatore, India","institution_ids":["https://openalex.org/I119668213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024020375","display_name":"J. Dinesh Peter","orcid":null},"institutions":[{"id":"https://openalex.org/I119668213","display_name":"Karunya University","ror":"https://ror.org/03k23nv15","country_code":"IN","type":"education","lineage":["https://openalex.org/I119668213"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"J. Dinesh Peter","raw_affiliation_strings":["Department of CSE Karunya Institute of Technology and Sciences  Coimbatore India","Department of CSE, Karunya Institute of Technology and Sciences, Coimbatore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE Karunya Institute of Technology and Sciences  Coimbatore India","institution_ids":["https://openalex.org/I119668213"]},{"raw_affiliation_string":"Department of CSE, Karunya Institute of Technology and Sciences, Coimbatore, India","institution_ids":["https://openalex.org/I119668213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057229501"],"corresponding_institution_ids":["https://openalex.org/I119668213"],"apc_list":{"value":3860,"currency":"USD","value_usd":3860},"apc_paid":null,"fwci":0.5318,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65920562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"43","issue":"6","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":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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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":0.9969000220298767,"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":0.9442456364631653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8982969522476196},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.819900393486023},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5272119045257568},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5269946455955505},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.48787689208984375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.463279664516449},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44335824251174927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4308483302593231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39747926592826843},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08926615118980408}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9442456364631653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8982969522476196},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.819900393486023},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5272119045257568},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5269946455955505},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.48787689208984375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.463279664516449},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44335824251174927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4308483302593231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39747926592826843},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08926615118980408},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1111/exsy.13392","is_oa":true,"landing_page_url":"https://doi.org/10.1111/exsy.13392","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/exsy.13392","source":{"id":"https://openalex.org/S72232612","display_name":"Expert Systems","issn_l":"0266-4720","issn":["0266-4720","1468-0394"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1111/exsy.13392","is_oa":true,"landing_page_url":"https://doi.org/10.1111/exsy.13392","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/exsy.13392","source":{"id":"https://openalex.org/S72232612","display_name":"Expert Systems","issn_l":"0266-4720","issn":["0266-4720","1468-0394"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383263774.pdf","grobid_xml":"https://content.openalex.org/works/W4383263774.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1956340063","https://openalex.org/W1995820507","https://openalex.org/W2022699557","https://openalex.org/W2064675550","https://openalex.org/W2078238240","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2124807415","https://openalex.org/W2131774270","https://openalex.org/W2139501017","https://openalex.org/W2143449221","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2526468814","https://openalex.org/W2527145521","https://openalex.org/W2745461083","https://openalex.org/W2963177403","https://openalex.org/W2963576560","https://openalex.org/W2963916161","https://openalex.org/W2963971014","https://openalex.org/W2964241990","https://openalex.org/W3009192917","https://openalex.org/W3010512657","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W4200197691","https://openalex.org/W4220848440","https://openalex.org/W4293087667","https://openalex.org/W4312545247","https://openalex.org/W4316082301"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417"],"abstract_inverted_index":{"Abstract":[0],"Automatic":[1],"Video":[2],"captioning":[3,139,194],"system":[4],"is":[5,122,141,168,233],"a":[6,13,28,45,81,96,105,113,125,142,237],"method":[7,71],"of":[8,37,53,80,144,173,182,201,222,317],"describing":[9],"the":[10,33,49,54,59,68,102,109,171,183,223,242,249,270,298,315,324],"content":[11,110],"in":[12,39,44,48,124,170,248,264,297],"video":[14,82,138,193],"by":[15],"analysing":[16],"its":[17,100,132],"visual":[18],"aspects":[19],"with":[20,58,153,256,283,288],"regard":[21],"to":[22,72,86,107,131,240,293],"space":[23],"and":[24,26,51,111,134,147,167,185,204,210,217,235,273,286,291,310],"time":[25],"producing":[27],"meaningful":[29],"caption":[30,56,79,120],"that":[31,207],"explains":[32],"video.":[34],"A":[35],"decade":[36],"research":[38,63],"this":[40,92],"area":[41],"has":[42,64,159,186,208,261,280],"resulted":[43],"steep":[46],"growth":[47],"quality":[50],"appropriateness":[52],"generated":[55,78,123],"compared":[57,287],"expected":[60,88],"result.":[61],"The":[62,119,137,196,231,278,300],"been":[65,262,281],"driven":[66],"from":[67,244],"very":[69,228],"basic":[70],"most":[73],"advanced":[74],"transformer":[75,197],"method.":[76],"Machine":[77],"must":[83,128],"be":[84,95,294],"adhering":[85],"many":[87],"standards.":[89],"For":[90],"humans,":[91],"task":[93],"may":[94],"trivial":[97],"one,":[98],"however":[99],"not":[101],"same":[103],"for":[104,117,192,258,306],"machine":[106],"analyse":[108],"generate":[112],"semantically":[114],"coherent":[115],"description":[116],"it.":[118],"which":[121,225],"natural":[126,148],"language":[127,149],"also":[129],"adhere":[130],"lexical":[133],"syntactical":[135],"structure.":[136],"process":[140],"culmination":[143],"computer":[145],"vision":[146],"processing":[150],"tasks.":[151],"Commencing":[152],"template":[154],"based":[155],"conventional":[156],"approach,":[157],"it":[158],"surpassed":[160],"statistical":[161],"method,":[162],"traditional":[163],"deep":[164],"learning":[165,319],"approaches":[166],"now":[169],"trend":[172],"using":[174],"transformers.":[175],"This":[176,267],"work":[177],"made":[178,199],"an":[179,188,202],"extensive":[180],"study":[181],"literature":[184],"proposed":[187],"improved":[189],"transformer\u2010based":[190],"architecture":[191,198],"process.":[195],"use":[200],"encoder":[203],"decoder":[205,232],"model":[206,224,243,255,268,279],"two":[209],"three":[211],"sublayers":[212],"respectively.":[213],"Multi\u2010head":[214],"self":[215],"attention":[216,219],"cross":[218],"are":[220,303],"part":[221],"bring":[226],"about":[227],"beneficial":[229],"results.":[230],"auto\u2010regressive":[234],"uses":[236],"masked":[238],"layer":[239],"prevent":[241],"foreseeing":[245],"future":[246],"words":[247],"caption.":[250],"An":[251],"enhanced":[252],"encoder\u2010decoder":[253],"Transformer":[254],"CNN":[257],"feature":[259],"extraction":[260],"used":[263],"our":[265],"work.":[266],"captures":[269],"long\u2010range":[271],"dependencies":[272],"temporal":[274],"relationships":[275],"more":[276],"effectively.":[277],"evaluated":[282],"benchmark":[284],"datasets":[285],"state\u2010of\u2010the\u2010art":[289],"methods":[290],"found":[292],"slightly":[295,304],"better":[296],"performance.":[299],"performance":[301],"scores":[302],"varying":[305],"BLEU,":[307],"METEOR,":[308],"ROUGE":[309],"CIDEr.":[311],"Furthermore,":[312],"we":[313],"propose":[314],"idea":[316],"curriculum":[318],"if":[320],"incorporated":[321],"can":[322],"improve":[323],"results":[325],"again.":[326]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}