{"id":"https://openalex.org/W4399749578","doi":"https://doi.org/10.1142/s2717554524500048","title":"Impact of Language-Specific Training on Image Caption Synthesis: A Case Study on Low-Resource Assamese Language","display_name":"Impact of Language-Specific Training on Image Caption Synthesis: A Case Study on Low-Resource Assamese Language","publication_year":2024,"publication_date":"2024-03-01","ids":{"openalex":"https://openalex.org/W4399749578","doi":"https://doi.org/10.1142/s2717554524500048"},"language":"en","primary_location":{"id":"doi:10.1142/s2717554524500048","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554524500048","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","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/A5005696798","display_name":"P Choudhury","orcid":"https://orcid.org/0009-0001-1159-3118"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Pankaj Choudhury","raw_affiliation_strings":["Centre for Linguistic Science and Technology, Indian Institute of Technology Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Centre for Linguistic Science and Technology, Indian Institute of Technology Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041308578","display_name":"Prithwijit Guha","orcid":"https://orcid.org/0000-0003-2885-0026"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prithwijit Guha","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053883070","display_name":"Sukumar Nandi","orcid":"https://orcid.org/0000-0002-5869-1057"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sukumar Nandi","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005696798"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":1.6498,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84224674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"01","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9890999794006348,"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":0.9872000217437744,"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/assamese","display_name":"Assamese","score":0.995919942855835},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9182157516479492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7716696262359619},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6218284368515015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5575244426727295},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4458511471748352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32561540603637695},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2516457438468933}],"concepts":[{"id":"https://openalex.org/C2777834912","wikidata":"https://www.wikidata.org/wiki/Q29401","display_name":"Assamese","level":2,"score":0.995919942855835},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9182157516479492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716696262359619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6218284368515015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575244426727295},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4458511471748352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32561540603637695},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2516457438468933},{"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:10.1142/s2717554524500048","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554524500048","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1969616664","https://openalex.org/W2559655401","https://openalex.org/W2612690371","https://openalex.org/W2745461083","https://openalex.org/W2800782462","https://openalex.org/W2803259101","https://openalex.org/W2886641317","https://openalex.org/W2896348597","https://openalex.org/W2963364170","https://openalex.org/W2986670728","https://openalex.org/W2990138404","https://openalex.org/W2990818246","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3138298063","https://openalex.org/W3168351812","https://openalex.org/W3216130706","https://openalex.org/W3216219070","https://openalex.org/W4283793362","https://openalex.org/W4389611355"],"related_works":["https://openalex.org/W2248864000","https://openalex.org/W2059553699","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284"],"abstract_inverted_index":{"Automatic":[0],"Image":[1],"Captioning":[2],"(AIC)":[3],"refers":[4],"to":[5,71,84,108,202],"the":[6,25,50,85,100,132,141,176],"process":[7],"of":[8,31,121,143,194],"synthesizing":[9],"semantically":[10],"and":[11,131,150,163,197,207],"syntactically":[12],"correct":[13],"descriptions":[14],"for":[15,39,49,75],"images.":[16,77],"Existing":[17],"research":[18],"on":[19,24,35,66,118,184,205],"AIC":[20,48,63,101],"has":[21],"predominantly":[22],"focused":[23,34],"English":[26,68,73,80,206],"language.":[27],"Comparatively,":[28],"lower":[29],"numbers":[30],"works":[32],"have":[33],"developing":[36],"captioning":[37],"systems":[38],"low-resource":[40],"Indian":[41],"languages":[42],"like":[43],"Assamese.":[44,113,211],"This":[45],"paper":[46],"investigates":[47],"Assamese":[51,86,105,185],"language":[52,87],"using":[53,88,103,157],"two":[54,119,177],"distinct":[55],"approaches.":[56],"The":[57,94,114,152,172],"first":[58],"approach":[59,96],"involves":[60,97],"utilizing":[61],"state-of-the-art":[62],"model":[64,102],"pretrained":[65,204],"an":[67,104],"image-caption":[69,106,186],"dataset":[70,107],"generate":[72],"captions":[74,81,110],"input":[76],"Next,":[78],"these":[79,144],"are":[82,116,155],"translated":[83,209],"a":[89,129,136],"publicly":[90],"available":[91],"automatic":[92,158],"translator.":[93],"second":[95],"exclusively":[98,183],"training":[99],"predict":[109],"directly":[111],"in":[112,192],"experiments":[115],"performed":[117],"types":[120],"state-of-art":[122],"models,":[123],"one":[124,134],"which":[125],"uses":[126,135],"LSTM":[127],"as":[128,161],"decoder":[130],"other":[133],"transformer.":[137],"Through":[138],"extensive":[139],"experimentation,":[140],"performance":[142],"approaches":[145,178],"is":[146,170],"evaluated":[147],"both":[148,191],"quantitatively":[149],"qualitatively.":[151],"quantitative":[153,195],"results":[154,190],"obtained":[156],"metrics":[159],"such":[160],"BLEU-n":[162],"CIDEr.":[164],"For":[165],"qualitative":[166,198],"analysis,":[167],"human":[168],"evaluation":[169],"performed.":[171],"comparative":[173],"performances":[174],"between":[175],"reveal":[179],"that":[180],"models":[181,203],"trained":[182],"datasets":[187],"achieve":[188],"superior":[189],"terms":[193],"measures":[196],"assessment":[199],"when":[200],"compared":[201],"subsequently":[208],"into":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}