{"id":"https://openalex.org/W4405271501","doi":"https://doi.org/10.1109/cvmi61877.2024.10781602","title":"Bengali Image Caption Generation using Attention Mechanism","display_name":"Bengali Image Caption Generation using Attention Mechanism","publication_year":2024,"publication_date":"2024-10-19","ids":{"openalex":"https://openalex.org/W4405271501","doi":"https://doi.org/10.1109/cvmi61877.2024.10781602"},"language":"en","primary_location":{"id":"doi:10.1109/cvmi61877.2024.10781602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi61877.2024.10781602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","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/A5061781283","display_name":"Sayantani De","orcid":null},"institutions":[{"id":"https://openalex.org/I195459967","display_name":"Mizoram University","ror":"https://ror.org/04b1m3e94","country_code":"IN","type":"education","lineage":["https://openalex.org/I195459967"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sayantani De","raw_affiliation_strings":["NIT Mizoram,Department of CSE,Aizawl,India"],"affiliations":[{"raw_affiliation_string":"NIT Mizoram,Department of CSE,Aizawl,India","institution_ids":["https://openalex.org/I195459967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077717775","display_name":"Ranjita Das","orcid":"https://orcid.org/0000-0001-6184-6294"},"institutions":[{"id":"https://openalex.org/I196486160","display_name":"National Institute of Technology Agartala","ror":"https://ror.org/03swyrn62","country_code":"IN","type":"education","lineage":["https://openalex.org/I196486160"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ranjita Das","raw_affiliation_strings":["NIT Agartala,Department of CSE,Agartala,India"],"affiliations":[{"raw_affiliation_string":"NIT Agartala,Department of CSE,Agartala,India","institution_ids":["https://openalex.org/I196486160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013536989","display_name":"Ashish Singh Patel","orcid":"https://orcid.org/0000-0002-2963-1039"},"institutions":[{"id":"https://openalex.org/I195459967","display_name":"Mizoram University","ror":"https://ror.org/04b1m3e94","country_code":"IN","type":"education","lineage":["https://openalex.org/I195459967"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Singh Patel","raw_affiliation_strings":["NIT Mizoram,Department of CSE,Aizawl,India"],"affiliations":[{"raw_affiliation_string":"NIT Mizoram,Department of CSE,Aizawl,India","institution_ids":["https://openalex.org/I195459967"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061781283"],"corresponding_institution_ids":["https://openalex.org/I195459967"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23396226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9926999807357788,"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":0.9923999905586243,"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":0.903680682182312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7570347785949707},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6817625761032104},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5395305752754211},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5378386974334717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076292753219604},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.37042689323425293}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.903680682182312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570347785949707},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6817625761032104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5395305752754211},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5378386974334717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076292753219604},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.37042689323425293},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvmi61877.2024.10781602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi61877.2024.10781602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1994461419","https://openalex.org/W2607579284","https://openalex.org/W2754051771","https://openalex.org/W2786852696","https://openalex.org/W2788237871","https://openalex.org/W2792245367","https://openalex.org/W2898424076","https://openalex.org/W2912290085","https://openalex.org/W2928165649","https://openalex.org/W2943568678","https://openalex.org/W2985745757","https://openalex.org/W2986670728","https://openalex.org/W2995836393","https://openalex.org/W2997428102","https://openalex.org/W2998404338","https://openalex.org/W3001281425","https://openalex.org/W3113708896","https://openalex.org/W3132832040","https://openalex.org/W3135053409","https://openalex.org/W3155399358","https://openalex.org/W3157177884","https://openalex.org/W3172293896","https://openalex.org/W3198243365","https://openalex.org/W3207264003","https://openalex.org/W3209745522","https://openalex.org/W3213610433","https://openalex.org/W4200298995","https://openalex.org/W4214698892","https://openalex.org/W4224138534","https://openalex.org/W4225330038","https://openalex.org/W6714414533"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W2794758919","https://openalex.org/W4232781930","https://openalex.org/W1913642778","https://openalex.org/W2630858571","https://openalex.org/W4300860228","https://openalex.org/W2329406070"],"abstract_inverted_index":{"Image":[0],"captioning":[1,17,116],"has":[2,128],"emerged":[3],"as":[4],"a":[5,48,112,152],"rapidly":[6],"thriving":[7],"area":[8],"for":[9,64,72,115],"the":[10,68,73,85,135,147],"machine":[11,30],"learning":[12,31],"research":[13],"community.":[14],"Generally,":[15],"image":[16,44,144],"is":[18,47,131],"performed":[19],"by":[20,54],"combining":[21],"various":[22,61],"computer":[23],"vision":[24],"features,":[25],"natural":[26],"language":[27,50,87,149],"processing,":[28],"and":[29,81,150],"methods":[32,63,83],"with":[33],"consideration":[34],"of":[35,155],"some":[36],"additional":[37],"inputs":[38],"to":[39,96,133],"get":[40],"more":[41],"accurate":[42],"context-dependent":[43],"captions":[45,66,145],"Bengali":[46,74,97,119,148],"significant":[49],"in":[51,67,84,118,137,146],"India,":[52],"adopted":[53],"approximately":[55],"100":[56],"million":[57],"people.":[58],"There":[59],"exist":[60],"state-of-the-art":[62],"generating":[65],"English":[69,86,95],"language;":[70],"however,":[71],"language,":[75],"there":[76],"are":[77,88],"very":[78],"limited":[79],"methods,":[80],"existing":[82],"not":[89],"particularly":[90],"helpful.":[91],"Moreover,":[92],"translations":[93],"from":[94],"may":[98],"overlook":[99],"or":[100,105],"misinterpret":[101],"subtle":[102],"meanings,":[103],"tones,":[104],"cultural":[106],"nuances.":[107],"Therefore,":[108],"this":[109,138],"work":[110],"proposes":[111],"machine-learning":[113],"model":[114,136],"pictures":[117],"using":[120],"an":[121],"attention":[122],"mechanism.":[123],"The":[124,140],"Flickr-8k":[125],"dataset,":[126],"which":[127],"8000":[129],"images,":[130],"used":[132],"train":[134],"work.":[139],"proposed":[141],"method":[142],"generates":[143],"attained":[151],"BLEU":[153],"score":[154],"0.66.":[156]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
