{"id":"https://openalex.org/W4389611355","doi":"https://doi.org/10.1109/ialp61005.2023.10337310","title":"Relevance of Language-Specific Training on Image Caption Synthesis for Low Resource Assamese Language","display_name":"Relevance of Language-Specific Training on Image Caption Synthesis for Low Resource Assamese Language","publication_year":2023,"publication_date":"2023-11-18","ids":{"openalex":"https://openalex.org/W4389611355","doi":"https://doi.org/10.1109/ialp61005.2023.10337310"},"language":"en","primary_location":{"id":"doi:10.1109/ialp61005.2023.10337310","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ialp61005.2023.10337310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Asian Language Processing (IALP)","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/A5049424240","display_name":"P. K. Choudhury","orcid":"https://orcid.org/0000-0002-1681-9753"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pankaj Choudhury","raw_affiliation_strings":["Centre for Linguistic Science and Technology"],"affiliations":[{"raw_affiliation_string":"Centre for Linguistic Science and Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041308578","display_name":"Prithwijit Guha","orcid":"https://orcid.org/0000-0003-2885-0026"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prithwijit Guha","raw_affiliation_strings":["Centre for Linguistic Science and Technology","Department of Electronics and Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"Centre for Linguistic Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Department of Electronics and Electrical Engineering","institution_ids":[]}]},{"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":["Indian Institute of Technology,Department of Computer Science and Engineering,Guwahati,Assam,India","Department of Computer Science and Engineering, Indian Institute of Technology, Guwahati, Assam, India","Centre for Linguistic Science and Technology"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Guwahati,Assam,India","institution_ids":["https://openalex.org/I1317621060"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]},{"raw_affiliation_string":"Centre for Linguistic Science and Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049424240"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44695996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.991599977016449,"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":0.9894999861717224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/assamese","display_name":"Assamese","score":0.9983618259429932},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8484423160552979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7352434396743774},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6287249326705933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6002192497253418},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5494461059570312},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.46190932393074036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3575114607810974},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2595463991165161}],"concepts":[{"id":"https://openalex.org/C2777834912","wikidata":"https://www.wikidata.org/wiki/Q29401","display_name":"Assamese","level":2,"score":0.9983618259429932},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8484423160552979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7352434396743774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6287249326705933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6002192497253418},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5494461059570312},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.46190932393074036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3575114607810974},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2595463991165161},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/ialp61005.2023.10337310","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ialp61005.2023.10337310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Asian Language Processing (IALP)","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":15,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W2130942839","https://openalex.org/W2745461083","https://openalex.org/W2792317186","https://openalex.org/W2803259101","https://openalex.org/W2963364170","https://openalex.org/W2986670728","https://openalex.org/W3035284526","https://openalex.org/W3138298063","https://openalex.org/W3216130706","https://openalex.org/W3216219070","https://openalex.org/W4287322030","https://openalex.org/W6630875275","https://openalex.org/W6679436768"],"related_works":["https://openalex.org/W70126818","https://openalex.org/W2059553699","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Automatic":[0],"Image":[1],"Captioning":[2],"(AIC)":[3],"is":[4,112],"the":[5,88,106,132,147],"process":[6],"of":[7,108],"generating":[8],"semantically":[9],"and":[10,105,116,121,144,152],"syntactically":[11],"correct":[12],"textual":[13],"descriptions":[14],"for":[15,38,49,72],"images.":[16],"Most":[17],"existing":[18],"research":[19],"on":[20,24,64,136,150],"AIC":[21,48,61,89],"have":[22,32,102],"focused":[23],"English":[25,65,70,151],"language.":[26],"In":[27],"comparison,":[28],"very":[29],"few":[30],"attempts":[31],"been":[33,103],"under-taken":[34],"to":[35,68,81,96,155],"synthesise":[36],"captions":[37,71,77],"low":[39],"resource":[40],"Indian":[41],"languages":[42],"like":[43],"Assamese.":[44,82,156],"This":[45],"paper":[46],"explores":[47],"Assamese":[50,93,98,137],"language":[51],"through":[52],"two":[53,110,128],"distinct":[54],"approaches.":[55],"The":[56,83,123],"first":[57],"approach":[58,85],"employs":[59],"state-of-art":[60],"model":[62,90],"pre-trained":[63],"image-caption":[66,94,138],"dataset":[67,95,139],"generate":[69],"an":[73,92],"input":[74],"image.":[75],"These":[76],"are":[78],"later":[79,153],"translated":[80],"second":[84],"exclusively":[86,134],"trains":[87],"using":[91,117],"predict":[97],"captions.":[99],"Extensive":[100],"experiments":[101],"conducted":[104],"performance":[107,124],"these":[109,127],"approaches":[111,129],"evaluated":[113],"both":[114],"qualitatively":[115,145],"quantitative":[118],"measures":[119],"(BLEU-n":[120],"CIDEr).":[122],"comparison":[125],"be-tween":[126],"reveals":[130],"that":[131],"models":[133,148],"trained":[135],"yields":[140],"better":[141],"results":[142],"quantitatively":[143],"than":[146],"pretrained":[149],"trans-lated":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}