{"id":"https://openalex.org/W3213345937","doi":"https://doi.org/10.23919/icac50006.2021.9594154","title":"Deep Learning Based Video Captioning in Bengali","display_name":"Deep Learning Based Video Captioning in Bengali","publication_year":2021,"publication_date":"2021-09-02","ids":{"openalex":"https://openalex.org/W3213345937","doi":"https://doi.org/10.23919/icac50006.2021.9594154","mag":"3213345937"},"language":"en","primary_location":{"id":"doi:10.23919/icac50006.2021.9594154","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icac50006.2021.9594154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 26th International Conference on Automation and Computing (ICAC)","raw_type":"proceedings-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/A5006997685","display_name":"Amir Hossain Raj","orcid":"https://orcid.org/0009-0007-7889-6352"},"institutions":[{"id":"https://openalex.org/I135564639","display_name":"Ahsanullah University of Science and Technology","ror":"https://ror.org/04wfbp123","country_code":"BD","type":"education","lineage":["https://openalex.org/I135564639"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Amir Hossain Raj","raw_affiliation_strings":["Ahsanullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ahsanullah University of Science and Technology","institution_ids":["https://openalex.org/I135564639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009700741","display_name":"Ashek Seum","orcid":"https://orcid.org/0000-0003-2468-6521"},"institutions":[{"id":"https://openalex.org/I135564639","display_name":"Ahsanullah University of Science and Technology","ror":"https://ror.org/04wfbp123","country_code":"BD","type":"education","lineage":["https://openalex.org/I135564639"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Ashek Seum","raw_affiliation_strings":["Ahsanullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ahsanullah University of Science and Technology","institution_ids":["https://openalex.org/I135564639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064666292","display_name":"Aurpan Dash","orcid":null},"institutions":[{"id":"https://openalex.org/I135564639","display_name":"Ahsanullah University of Science and Technology","ror":"https://ror.org/04wfbp123","country_code":"BD","type":"education","lineage":["https://openalex.org/I135564639"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Aurpan Dash","raw_affiliation_strings":["Ahsanullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ahsanullah University of Science and Technology","institution_ids":["https://openalex.org/I135564639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702353","display_name":"Saiful Islam","orcid":"https://orcid.org/0000-0001-8782-0279"},"institutions":[{"id":"https://openalex.org/I135564639","display_name":"Ahsanullah University of Science and Technology","ror":"https://ror.org/04wfbp123","country_code":"BD","type":"education","lineage":["https://openalex.org/I135564639"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Saiful Islam","raw_affiliation_strings":["Ahsanullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ahsanullah University of Science and Technology","institution_ids":["https://openalex.org/I135564639"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042654567","display_name":"Faisal Muhammad Shah","orcid":"https://orcid.org/0000-0002-5118-8571"},"institutions":[{"id":"https://openalex.org/I135564639","display_name":"Ahsanullah University of Science and Technology","ror":"https://ror.org/04wfbp123","country_code":"BD","type":"education","lineage":["https://openalex.org/I135564639"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Faisal Muhammad Shah","raw_affiliation_strings":["Ahsanullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ahsanullah University of Science and Technology","institution_ids":["https://openalex.org/I135564639"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135564639"],"apc_list":null,"apc_paid":null,"fwci":0.5822,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69374033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976999759674072,"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":0.9927999973297119,"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/bengali","display_name":"Bengali","score":0.9843764305114746},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9501386880874634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8804054260253906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6761188507080078},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6353424191474915},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6147938370704651},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5473664999008179},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5267835259437561},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4889024794101715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46813902258872986},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4337584674358368},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31542497873306274}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9843764305114746},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9501386880874634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8804054260253906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6761188507080078},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6353424191474915},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6147938370704651},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5473664999008179},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5267835259437561},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4889024794101715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46813902258872986},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4337584674358368},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31542497873306274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/icac50006.2021.9594154","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icac50006.2021.9594154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 26th International Conference on Automation and Computing (ICAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2549139847","https://openalex.org/W2950577311","https://openalex.org/W2953461088","https://openalex.org/W2962861647","https://openalex.org/W2963364170","https://openalex.org/W2965558087","https://openalex.org/W2982151937","https://openalex.org/W2985051484","https://openalex.org/W2986670728","https://openalex.org/W3035265375","https://openalex.org/W3046370984","https://openalex.org/W3124433782","https://openalex.org/W3133511908","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6723250868","https://openalex.org/W6769562027","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4210416330","https://openalex.org/W4281398254","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Generating":[0],"meaningful":[1,65],"textual":[2],"descriptions":[3],"from":[4],"visual":[5],"contents":[6],"having":[7],"the":[8,34,68,106,116,139,143,153,168,186],"context":[9],"in":[10,15,42,73,122],"consideration":[11],"is":[12,39,51,78,184],"very":[13],"challenging":[14],"terms":[16],"of":[17,36,70,88,119,142],"Natural":[18],"Language":[19],"Processing":[20],"(NLP)":[21],"and":[22,26,96,108,163,171,175,180],"Computer":[23],"Vision":[24],"(CV)":[25],"video":[27,37,72,129],"captioning":[28,38,196],"adds":[29],"more":[30],"to":[31,63,149],"it.":[32],"Currently,":[33],"field":[35,124],"highly":[40],"explored":[41],"different":[43,89],"languages":[44],"except":[45],"for":[46],"Bengali,":[47],"where":[48],"no":[49,128],"work":[50],"available":[52],"so":[53],"far.":[54],"In":[55,157],"this":[56,123,136,158],"paper,":[57],"we":[58,160],"have":[59,146,161],"proposed":[60,76],"a":[61,71,86,173],"model":[62,77,166],"generate":[64],"captions":[66,141],"describing":[67],"activities":[69],"Bengali.":[74],"The":[75],"an":[79],"encoder-decoder-based":[80],"novel":[81],"deep":[82],"architecture":[83],"that":[84],"incorporates":[85],"combination":[87],"Convolutional":[90],"Neural":[91],"Networks":[92],"(CNNs),":[93],"like":[94],"2D-CNN":[95],"3D-CNN":[97],"with":[98,127,131,191],"Bidirectional":[99],"Long":[100,110],"Short":[101,111],"Term":[102,112],"Memory":[103,113],"(Bi-LSTM)":[104],"as":[105,115],"encoder":[107],"two-layer":[109],"(LSTM)":[114],"decoder.":[117],"Lack":[118],"proper":[120,132],"concern":[121],"left":[125],"us":[126],"dataset":[130,145,170],"Bengali":[133,150,194],"captions.":[134],"For":[135],"reason,":[137],"all":[138],"English":[140],"MSVD":[144,169],"been":[147],"translated":[148],"language":[151],"using":[152],"Google":[154],"Translate":[155],"API.":[156],"work,":[159],"trained":[162],"evaluated":[164],"our":[165],"on":[167,178],"achieved":[172],"32.6%,":[174],"51.2%":[176],"score":[177],"BLEU":[179],"CIDEr,":[181],"respectively,":[182],"which":[183],"currently":[185],"state-of-the-art":[187],"result":[188],"even":[189],"compared":[190],"closely":[192],"related":[193],"image":[195],"works.":[197]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
