{"id":"https://openalex.org/W4404037696","doi":"https://doi.org/10.1109/mlsp58920.2024.10734813","title":"Nature-based Bengali Picture Captioning using Global Attention with GRU","display_name":"Nature-based Bengali Picture Captioning using Global Attention with GRU","publication_year":2024,"publication_date":"2024-09-22","ids":{"openalex":"https://openalex.org/W4404037696","doi":"https://doi.org/10.1109/mlsp58920.2024.10734813"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp58920.2024.10734813","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp58920.2024.10734813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://openaccess.city.ac.uk/id/eprint/34304/1/Fateema_NU_Image_Captioning.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000607701","display_name":"Fatema Tuz Zohora","orcid":null},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Fatema Tuz Zohora","raw_affiliation_strings":["Northumbria University,Department of Computer and Information Science,London,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northumbria University,Department of Computer and Information Science,London,United Kingdom","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013042584","display_name":"Sujit K. Biswas","orcid":"https://orcid.org/0000-0001-6993-7908"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sujit Biswas","raw_affiliation_strings":["City University of London,Department of Computer Science,London,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of London,Department of Computer Science,London,United Kingdom","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019217199","display_name":"Anupam Kumar Bairagi","orcid":"https://orcid.org/0000-0003-1639-1301"},"institutions":[{"id":"https://openalex.org/I124386471","display_name":"Khulna University","ror":"https://ror.org/05pny7s12","country_code":"BD","type":"education","lineage":["https://openalex.org/I124386471"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Anupam Kumar Bairagi","raw_affiliation_strings":["Khulna University,Department of Computer Science and Engineering,Khulna,Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khulna University,Department of Computer Science and Engineering,Khulna,Bangladesh","institution_ids":["https://openalex.org/I124386471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090688531","display_name":"Kashif Sharif","orcid":"https://orcid.org/0000-0001-7214-6568"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kashif Sharif","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology (BIT),Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology (BIT),Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000607701"],"corresponding_institution_ids":["https://openalex.org/I32394136"],"apc_list":null,"apc_paid":null,"fwci":0.4591,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64728053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9911999702453613,"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":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.965910792350769},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9555221199989319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6675246953964233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49822449684143066},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45424684882164},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34366732835769653},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27395761013031006}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.965910792350769},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9555221199989319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6675246953964233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49822449684143066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45424684882164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34366732835769653},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27395761013031006}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp58920.2024.10734813","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp58920.2024.10734813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.city.ac.uk:34304","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/sujit=2Ebiswas.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/34304/1/Fateema_NU_Image_Captioning.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:openaccess.city.ac.uk:34304","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/sujit=2Ebiswas.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/34304/1/Fateema_NU_Image_Captioning.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404037696.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2101105183","https://openalex.org/W2133564696","https://openalex.org/W2418300416","https://openalex.org/W2963364170","https://openalex.org/W2963778889","https://openalex.org/W2977970283","https://openalex.org/W2985745757","https://openalex.org/W2997942948","https://openalex.org/W3032651662","https://openalex.org/W3036848992","https://openalex.org/W3065661397","https://openalex.org/W3128663629","https://openalex.org/W3132423244","https://openalex.org/W3153200530","https://openalex.org/W3154825838","https://openalex.org/W3155399358","https://openalex.org/W3209417397","https://openalex.org/W3216219070","https://openalex.org/W4206111836","https://openalex.org/W4281398254","https://openalex.org/W4281774797","https://openalex.org/W4283793919","https://openalex.org/W4289785095","https://openalex.org/W4317564503","https://openalex.org/W4319996369","https://openalex.org/W4321080401","https://openalex.org/W4321479797","https://openalex.org/W4323341874","https://openalex.org/W4323824384","https://openalex.org/W4367674159","https://openalex.org/W4386066385","https://openalex.org/W4389009503","https://openalex.org/W6679434410","https://openalex.org/W6841755765"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W4210416330","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W4281398254","https://openalex.org/W2028401451","https://openalex.org/W2769530083","https://openalex.org/W3161006337","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automatic":[0],"picture":[1,39],"captioning":[2,40],"is":[3],"a":[4,28,60,95,106,114,172],"prominent":[5],"re-search":[6],"area":[7],"of":[8,31,63,81,99,117,149,175],"artificial":[9],"intelligence":[10],"technology":[11],"(AI).":[12],"Its":[13],"ability":[14],"to":[15,112],"enhance":[16],"AI":[17],"models":[18,91,111,132,160],"by":[19],"translating":[20],"observed":[21],"data":[22],"into":[23],"human":[24],"language":[25,44],"opens":[26],"up":[27],"wide":[29],"range":[30],"real-time":[32],"applications.":[33],"In":[34,177],"this":[35,56,134],"study,":[36],"we":[37,58,77,126],"explore":[38],"in":[41,55,188],"the":[42,46,51,69,73,79,110,162,167,179,182],"Bengali":[43],"using":[45,133,161,181],"global":[47,66],"attention":[48,67],"mechanism.":[49],"Given":[50],"limited":[52],"prior":[53],"research":[54,124],"area,":[57],"provide":[59],"comprehensive":[61],"assessment":[62],"two":[64,82],"distinct":[65],"approaches:":[68],"general":[70,183],"approach":[71,184],"and":[72,86,128,141],"concatenation":[74,163],"approach.":[75],"Additionally,":[76],"evaluate":[78],"performance":[80],"CNN":[83],"encoders,":[84],"VGG19":[85,186],"InceptionV3,within":[87],"these":[88,145],"models.":[89],"The":[90,156],"are":[92,147],"trained":[93,129],"on":[94],"secondary":[96],"dataset":[97],"consisting":[98],"4,849":[100],"nature-based":[101],"images,":[102],"each":[103],"annotated":[104],"with":[105,166,185],"single":[107],"caption,":[108],"enabling":[109],"gain":[113],"broad":[115],"understanding":[116],"related":[118],"categorical":[119],"information.":[120],"To":[121],"achieve":[122],"our":[123],"objectives,":[125],"developed":[127],"four":[130],"separate":[131],"new":[135],"dataset.":[136],"Our":[137],"analysis,":[138],"both":[139],"qualitative":[140],"quantitative,":[142],"demonstrates":[143],"that":[144,159],"algorithms":[146],"capable":[148],"generating":[150,189],"human-like":[151],"captions":[152],"for":[153],"similar":[154],"images.":[155],"results":[157],"indicate":[158],"approach,":[164],"particu-larly":[165],"InceptionV3encoder,":[168],"performed":[169],"best,":[170],"achieving":[171],"BLEU-1":[173],"score":[174],"84.85.":[176],"contrast,":[178],"model":[180],"underperformed":[187],"satisfactory":[190],"captions.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}