{"id":"https://openalex.org/W4390552097","doi":"https://doi.org/10.1109/iscit57293.2023.10376080","title":"Automatic Bengali Image Captioning using EfficientNet-Transformer Network","display_name":"Automatic Bengali Image Captioning using EfficientNet-Transformer Network","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4390552097","doi":"https://doi.org/10.1109/iscit57293.2023.10376080"},"language":"en","primary_location":{"id":"doi:10.1109/iscit57293.2023.10376080","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscit57293.2023.10376080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 22nd International Symposium on Communications and Information Technologies (ISCIT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5048525091","display_name":"Muhammad Khubayeeb Kabir","orcid":"https://orcid.org/0000-0001-6868-8882"},"institutions":[{"id":"https://openalex.org/I5518804","display_name":"BRAC University","ror":"https://ror.org/00sge8677","country_code":"BD","type":"education","lineage":["https://openalex.org/I5518804"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Muhammad Khubayeeb Kabir","raw_affiliation_strings":["BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I5518804"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I5518804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093647543","display_name":"Anindita Labonno","orcid":null},"institutions":[{"id":"https://openalex.org/I5518804","display_name":"BRAC University","ror":"https://ror.org/00sge8677","country_code":"BD","type":"education","lineage":["https://openalex.org/I5518804"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Anindita Labonno","raw_affiliation_strings":["BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I5518804"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I5518804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113087895","display_name":"Sofia Amin","orcid":null},"institutions":[{"id":"https://openalex.org/I5518804","display_name":"BRAC University","ror":"https://ror.org/00sge8677","country_code":"BD","type":"education","lineage":["https://openalex.org/I5518804"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Sofia Amin","raw_affiliation_strings":["BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I5518804"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I5518804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093647544","display_name":"Fariha Tahsin","orcid":null},"institutions":[{"id":"https://openalex.org/I5518804","display_name":"BRAC University","ror":"https://ror.org/00sge8677","country_code":"BD","type":"education","lineage":["https://openalex.org/I5518804"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Fariha Tahsin","raw_affiliation_strings":["BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I5518804"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I5518804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074858619","display_name":"Md. Khalilur Rhaman","orcid":"https://orcid.org/0000-0001-7796-8018"},"institutions":[{"id":"https://openalex.org/I5518804","display_name":"BRAC University","ror":"https://ror.org/00sge8677","country_code":"BD","type":"education","lineage":["https://openalex.org/I5518804"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Khalilur Rhaman","raw_affiliation_strings":["BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I5518804"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I5518804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019896373","display_name":"Moin Mostakim","orcid":null},"institutions":[{"id":"https://openalex.org/I5518804","display_name":"BRAC University","ror":"https://ror.org/00sge8677","country_code":"BD","type":"education","lineage":["https://openalex.org/I5518804"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Moin Mostakim","raw_affiliation_strings":["BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BRAC University,Department of Computer Science and Engineering,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I5518804"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I5518804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5518804"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs/2101.10804","issue":null,"first_page":"110","last_page":"115"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9868000149726868,"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":0.9020000696182251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8342423439025879},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8186010122299194},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7905054092407227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5949727892875671},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5772156715393066},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5054786205291748},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46289342641830444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3837779760360718},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.28268927335739136},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0891309380531311},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08133688569068909},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06404301524162292}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9020000696182251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342423439025879},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8186010122299194},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7905054092407227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5949727892875671},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5772156715393066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5054786205291748},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46289342641830444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3837779760360718},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28268927335739136},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0891309380531311},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08133688569068909},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06404301524162292},{"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:10.1109/iscit57293.2023.10376080","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscit57293.2023.10376080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 22nd International Symposium on Communications and Information Technologies (ISCIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2053233826","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2592949994","https://openalex.org/W2963364170","https://openalex.org/W2964350391","https://openalex.org/W2965558087","https://openalex.org/W2981165461","https://openalex.org/W3033210410","https://openalex.org/W3094502228","https://openalex.org/W3124149278","https://openalex.org/W3124433782","https://openalex.org/W3132423244","https://openalex.org/W3134450428","https://openalex.org/W3154825838","https://openalex.org/W3209417397","https://openalex.org/W3216219070","https://openalex.org/W6620707391","https://openalex.org/W6763360694","https://openalex.org/W6784333009","https://openalex.org/W6789705400"],"related_works":["https://openalex.org/W4281398254","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/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417"],"abstract_inverted_index":{"The":[0,114],"task":[1],"of":[2,17,46,55,60,95],"image":[3,70],"captioning":[4,71],"is":[5],"a":[6,65,74,86,103,108],"complex":[7],"process":[8],"that":[9,72,106],"involves":[10,73],"generating":[11],"textual":[12],"descriptions":[13],"for":[14],"images.":[15],"Much":[16],"the":[18,44,47,53,58,93,120],"research":[19,41,56],"done":[20],"in":[21,57],"this":[22],"particular":[23],"domain,":[24],"especially":[25],"using":[26,125],"transformer":[27],"models,":[28],"has":[29,37],"been":[30,38],"focused":[31],"on":[32,112,119],"English":[33],"language.":[34,49],"However,":[35],"there":[36],"relatively":[39],"little":[40],"dedicated":[42],"to":[43,68],"context":[45,59],"Bengali":[48,61],"This":[50],"study":[51],"addresses":[52],"lack":[54],"language":[62],"and":[63,123],"proposes":[64],"novel":[66],"approach":[67,84],"automatic":[69],"multi-modal,":[75],"transformer-based,":[76],"end-to-end":[77],"model":[78,101],"with":[79,102],"an":[80],"encoder-decoder":[81],"architecture.":[82],"Our":[83],"utilizes":[85,107],"pre-trained":[87,111],"EfficientNet":[88],"Transformer":[89,105],"Network.":[90],"To":[91],"evaluate":[92],"effectiveness":[94],"our":[96,100],"approach,":[97],"we":[98],"compare":[99],"Vision":[104],"non-convolutional":[109],"encoder":[110],"ImageNet.":[113],"two":[115],"models":[116],"were":[117],"tested":[118],"BanglaLekhaImageCaptions":[121],"dataset":[122],"evaluated":[124],"BLEU":[126],"metrics.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}