{"id":"https://openalex.org/W3080672672","doi":"https://doi.org/10.4018/ijgcms.2020040103","title":"A Deep Structured Model for Video Captioning","display_name":"A Deep Structured Model for Video Captioning","publication_year":2020,"publication_date":"2020-04-01","ids":{"openalex":"https://openalex.org/W3080672672","doi":"https://doi.org/10.4018/ijgcms.2020040103","mag":"3080672672"},"language":"en","primary_location":{"id":"doi:10.4018/ijgcms.2020040103","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijgcms.2020040103","pdf_url":null,"source":{"id":"https://openalex.org/S60769682","display_name":"International Journal of Gaming and Computer-Mediated Simulations","issn_l":"1942-3888","issn":["1942-3888","1942-3896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Gaming and Computer-Mediated Simulations","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/A5102975520","display_name":"V. Vinodhini","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"V. Vinodhini","raw_affiliation_strings":["Sona College of Technology, India"],"affiliations":[{"raw_affiliation_string":"Sona College of Technology, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021509278","display_name":"B. Sathiyabhama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B. Sathiyabhama","raw_affiliation_strings":["Sona College of Technology, India"],"affiliations":[{"raw_affiliation_string":"Sona College of Technology, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112692971","display_name":"S. Sankar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Sankar","raw_affiliation_strings":["Sona College of Technology, India"],"affiliations":[{"raw_affiliation_string":"Sona College of Technology, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019927665","display_name":"Somula Ramasubbareddy","orcid":"https://orcid.org/0000-0002-3306-6589"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramasubbareddy Somula","raw_affiliation_strings":["Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, India"],"affiliations":[{"raw_affiliation_string":"Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102975520"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5897,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.69378563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"12","issue":"2","first_page":"44","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.9991000294685364,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.87111496925354},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.842832088470459},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7811002731323242},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6503711938858032},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5964604616165161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5959491729736328},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5765897035598755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4690072238445282},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4370816648006439},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4275313913822174},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4167092442512512},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37914174795150757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.87111496925354},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.842832088470459},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7811002731323242},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6503711938858032},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5964604616165161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5959491729736328},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5765897035598755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4690072238445282},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4370816648006439},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4275313913822174},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4167092442512512},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37914174795150757},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4018/ijgcms.2020040103","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijgcms.2020040103","pdf_url":null,"source":{"id":"https://openalex.org/S60769682","display_name":"International Journal of Gaming and Computer-Mediated Simulations","issn_l":"1942-3888","issn":["1942-3888","1942-3896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Gaming and Computer-Mediated Simulations","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2899879331","https://openalex.org/W2905654560","https://openalex.org/W2907342958","https://openalex.org/W2913822893","https://openalex.org/W2922319990","https://openalex.org/W2945223572","https://openalex.org/W2963929112","https://openalex.org/W3104915307"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Video":[0],"captions":[1],"help":[2],"people":[3,18],"to":[4,22,143,164,177],"understand":[5,23],"in":[6,86,91,111],"a":[7,52,58,96,112,130],"noisy":[8],"environment":[9],"or":[10],"when":[11],"the":[12,30,38,120,123,145,166,173,179,183],"sound":[13],"is":[14,57,83,101,126,141,149,162,186],"muted.":[15],"It":[16],"helps":[17],"having":[19],"impaired":[20],"hearing":[21],"much":[24],"better.":[25],"Captions":[26],"not":[27],"only":[28],"support":[29],"content":[31],"creators":[32],"and":[33,48,77,108],"translators":[34],"but":[35],"also":[36],"boost":[37],"search":[39],"engine":[40],"optimization.":[41],"Many":[42],"advanced":[43],"areas":[44],"like":[45],"computer":[46],"vision":[47],"human-computer":[49],"interaction":[50],"play":[51],"vital":[53],"role":[54],"as":[55],"there":[56],"successful":[59],"growth":[60],"of":[61,88],"deep":[62,68,97],"learning":[63,69],"techniques.":[64],"Numerous":[65],"surveys":[66],"on":[67],"models":[70],"are":[71],"evolved":[72],"with":[73,80],"different":[74],"methods,":[75],"architecture,":[76],"metrics.":[78],"Working":[79],"video":[81,184],"subtitles":[82],"still":[84],"challenging":[85],"terms":[87],"activity":[89,104],"recognition":[90],"video.":[92],"This":[93],"paper":[94],"proposes":[95],"structured":[98],"model":[99,140,160],"that":[100],"effective":[102],"towards":[103],"recognition,":[105],"automatically":[106],"classifies":[107],"caption":[109],"it":[110,171],"single":[113],"architecture.":[114],"The":[115,147],"first":[116],"process":[117],"includes":[118],"subtracting":[119],"foreground":[121],"from":[122],"background;":[124],"this":[125],"done":[127,150],"by":[128,188],"building":[129],"3D":[131],"convolutional":[132],"neural":[133],"network":[134],"(CNN)":[135],"model.":[136],"A":[137,157],"Gaussian":[138],"mixture":[139],"used":[142,163],"remove":[144],"backdrop.":[146],"classification":[148],"using":[151,189],"long":[152],"short-term":[153],"memory":[154],"networks":[155],"(LSTM).":[156],"hidden":[158],"Markov":[159],"(HMM)":[161],"generate":[165],"high":[167],"quality":[168],"data.":[169],"Next,":[170],"uses":[172],"nonlinear":[174],"activation":[175],"function":[176],"perform":[178],"normalization":[180],"process.":[181],"Finally,":[182],"captioning":[185],"achieved":[187],"natural":[190],"language.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}
