{"id":"https://openalex.org/W4407583788","doi":"https://doi.org/10.1145/3717612","title":"Exploring Semantic Attributes for Image Caption Synthesis in Low-Resource Assamese Language","display_name":"Exploring Semantic Attributes for Image Caption Synthesis in Low-Resource Assamese Language","publication_year":2025,"publication_date":"2025-02-14","ids":{"openalex":"https://openalex.org/W4407583788","doi":"https://doi.org/10.1145/3717612"},"language":"en","primary_location":{"id":"doi:10.1145/3717612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3717612","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information 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":["Center For lingustics Science and Technology, Indian Institute of Technology Guwahati, Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Center For lingustics Science and Technology, Indian Institute of Technology Guwahati, Guwahati, 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":["Electronics & Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Electronics & Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, 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":["Computer Science and Engineering, Indian Institute of Technology Guwahati, Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Guwahati, Guwahati, 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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02250984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"4","first_page":"1","last_page":"21"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9921000003814697,"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":0.9850999712944031,"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":0.9241311550140381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6282089352607727},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5522527098655701},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46867117285728455},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3765597641468048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34280505776405334},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32788264751434326},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.061692893505096436}],"concepts":[{"id":"https://openalex.org/C2777834912","wikidata":"https://www.wikidata.org/wiki/Q29401","display_name":"Assamese","level":2,"score":0.9241311550140381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6282089352607727},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5522527098655701},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46867117285728455},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3765597641468048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34280505776405334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32788264751434326},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.061692893505096436},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3717612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3717612","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1969616664","https://openalex.org/W2108598243","https://openalex.org/W2112912048","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2284177844","https://openalex.org/W2302086703","https://openalex.org/W2493916176","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2575842049","https://openalex.org/W2613718673","https://openalex.org/W2624317482","https://openalex.org/W2732026016","https://openalex.org/W2745461083","https://openalex.org/W2792317186","https://openalex.org/W2803259101","https://openalex.org/W2896348597","https://openalex.org/W2911285743","https://openalex.org/W2916009164","https://openalex.org/W2950626540","https://openalex.org/W2963084599","https://openalex.org/W2963364170","https://openalex.org/W2964018924","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3124433782","https://openalex.org/W3138298063","https://openalex.org/W3153200530","https://openalex.org/W3200513480","https://openalex.org/W3216219070","https://openalex.org/W4200435073","https://openalex.org/W4213207626","https://openalex.org/W4230167808","https://openalex.org/W4317600295","https://openalex.org/W4399749578","https://openalex.org/W6679436768","https://openalex.org/W6739901393","https://openalex.org/W6740934225"],"related_works":["https://openalex.org/W70126818","https://openalex.org/W1993273011","https://openalex.org/W2595800753","https://openalex.org/W2951796583","https://openalex.org/W2795118711","https://openalex.org/W3136670730","https://openalex.org/W4225398085","https://openalex.org/W4294250292","https://openalex.org/W2891067899","https://openalex.org/W3111362937"],"abstract_inverted_index":{"Research":[0],"on":[1,8,203],"image":[2,55,103,114],"caption":[3,193],"generation":[4],"has":[5],"predominantly":[6],"focused":[7],"resource-rich":[9],"languages":[10,15],"like":[11],"English,":[12],"leaving":[13],"resource-poor":[14],"(like":[16],"Assamese":[17,40,73,131,192],"and":[18,31,95,128,161,176,181],"several":[19],"others)":[20],"largely":[21],"understudied.":[22],"In":[23],"this":[24,26],"context,":[25],"paper":[27],"leverages":[28],"both":[29,157,174],"visual":[30],"semantic":[32,68,96,120],"attribute":[33],"based":[34],"features":[35,65,91],"for":[36,87,148],"generating":[37],"captions":[38],"in":[39,70,191],"language.":[41,74],"Semantic":[42],"attributes":[43],"refer":[44],"to":[45,106,109,124,143,196],"the":[46,54,61,79,88,102,113,118,134,145,168,204],"significant":[47,188],"words":[48,69],"that":[49],"represent":[50],"higher-level":[51],"knowledge":[52],"about":[53],"content.":[56],"This":[57],"work":[58],"contributes":[59],"through":[60,173],"effective":[62],"use":[63],"of":[64,81,90,112,167],"derived":[66,92],"from":[67,93],"low":[71],"resource":[72],"The":[75,98,151,165,184],"second":[76],"contribution":[77],"is":[78,137,153,171],"proposal":[80],"a":[82,140],"Visual-Semantic":[83],"Self-Attention":[84],"(VSSA)":[85],"module":[86,100,136],"combination":[89],"images":[94],"attributes.":[97],"VSSA":[99,135],"enables":[101],"captioning":[104],"model":[105,142,152,170,186],"dynamically":[107],"attend":[108],"relevant":[110,127],"regions":[111],"as":[115,117],"well":[116],"important":[119],"attributes,":[121],"thereby":[122],"leading":[123],"more":[125],"contextually":[126],"linguistically":[129],"accurate":[130],"captions.":[132],"Moreover,":[133],"incorporated":[138],"into":[139],"Transformer":[141],"leverage":[144],"stacked":[146],"attention":[147],"performance":[149,189],"improvement.":[150],"trained":[154],"by":[155],"using":[156],"cross-entropy":[158],"loss":[159],"optimization":[160],"reinforcement":[162],"learning":[163],"approach.":[164],"effectiveness":[166],"proposed":[169,185],"evaluated":[172],"qualitative":[175],"quantitative":[177],"analyses":[178],"(using":[179],"BLEU-n":[180],"CIDEr":[182,201],"metrics).":[183],"shows":[187],"improvement":[190],"synthesis":[194],"compared":[195],"previous":[197],"methods,":[198],"achieving":[199],"93.7%":[200],"score":[202],"COCO-Assamese":[205],"Caption":[206],"(COCO-AC)":[207],"dataset.":[208]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}