{"id":"https://openalex.org/W4393342149","doi":"https://doi.org/10.1145/3654796","title":"A Novel Pretrained General-purpose Vision Language Model for the Vietnamese Language","display_name":"A Novel Pretrained General-purpose Vision Language Model for the Vietnamese Language","publication_year":2024,"publication_date":"2024-03-30","ids":{"openalex":"https://openalex.org/W4393342149","doi":"https://doi.org/10.1145/3654796"},"language":"en","primary_location":{"id":"doi:10.1145/3654796","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654796","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654796","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3654796","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064249292","display_name":"\u0110inh Nh\u1eadt V\u0169","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dinh Anh Vu","raw_affiliation_strings":["University of Science and Technology of Hanoi, Hanoi, Viet Nam","ICTLab, University of Science and Technology of Hanoi, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-8071-7962","affiliations":[{"raw_affiliation_string":"University of Science and Technology of Hanoi, Hanoi, Viet Nam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"ICTLab, University of Science and Technology of Hanoi, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022117655","display_name":"Quang Nhat Minh Pham","orcid":"https://orcid.org/0000-0002-0570-4619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quang Nhat Minh Pham","raw_affiliation_strings":["Aimesoft JSC, Hanoi Viet Nam"],"raw_orcid":"https://orcid.org/0000-0002-0570-4619","affiliations":[{"raw_affiliation_string":"Aimesoft JSC, Hanoi Viet Nam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053869498","display_name":"Giang Son Tran","orcid":"https://orcid.org/0000-0001-7140-6882"},"institutions":[{"id":"https://openalex.org/I70349855","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50","country_code":"VN","type":"government","lineage":["https://openalex.org/I70349855"]},{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Giang Son Tran","raw_affiliation_strings":["University of Science and Technology of Hanoi, Hanoi, Viet Nam","ICTLab, University of Science and Technology of Hanoi, Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Cau Giay, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0001-7140-6882","affiliations":[{"raw_affiliation_string":"University of Science and Technology of Hanoi, Hanoi, Viet Nam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"ICTLab, University of Science and Technology of Hanoi, Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Cau Giay, Hanoi, Vietnam","institution_ids":["https://openalex.org/I70349855","https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.329,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49620039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"23","issue":"5","first_page":"1","last_page":"16"},"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":0.9860000014305115,"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/T10028","display_name":"Topic Modeling","score":0.9832000136375427,"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/computer-science","display_name":"Computer science","score":0.8858745098114014},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8665574789047241},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7639358639717102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6970394849777222},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6880741119384766},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.6557247042655945},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6516854763031006},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5740960836410522},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5733448266983032},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4868178069591522},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.47693222761154175},{"id":"https://openalex.org/keywords/clef","display_name":"Clef","score":0.4182327687740326},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39679154753685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35540974140167236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8858745098114014},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8665574789047241},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7639358639717102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6970394849777222},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6880741119384766},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.6557247042655945},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6516854763031006},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5740960836410522},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5733448266983032},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4868178069591522},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47693222761154175},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.4182327687740326},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39679154753685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35540974140167236},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3654796","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654796","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654796","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":{"id":"doi:10.1145/3654796","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654796","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654796","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393342149.pdf","grobid_xml":"https://content.openalex.org/works/W4393342149.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1575833922","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2560730294","https://openalex.org/W2741631785","https://openalex.org/W2796108585","https://openalex.org/W2886641317","https://openalex.org/W2904565150","https://openalex.org/W2916009164","https://openalex.org/W2951798058","https://openalex.org/W2963115613","https://openalex.org/W2963518342","https://openalex.org/W2963530300","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2979826702","https://openalex.org/W2981852735","https://openalex.org/W2990138404","https://openalex.org/W2997591391","https://openalex.org/W3014611590","https://openalex.org/W3035652667","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3098637735","https://openalex.org/W3104279398","https://openalex.org/W3104636952","https://openalex.org/W3110662498","https://openalex.org/W3139732141","https://openalex.org/W3164901500","https://openalex.org/W3166396011","https://openalex.org/W3174010726","https://openalex.org/W3177654849","https://openalex.org/W3193402170","https://openalex.org/W3195577433","https://openalex.org/W3198196812","https://openalex.org/W3209532394","https://openalex.org/W3210390771","https://openalex.org/W3213351348","https://openalex.org/W4225683910","https://openalex.org/W4225832925","https://openalex.org/W4225871896","https://openalex.org/W4280557512","https://openalex.org/W4284670680","https://openalex.org/W4286970289","https://openalex.org/W4287176715","https://openalex.org/W4287873420","https://openalex.org/W4288089799","https://openalex.org/W4296406182","https://openalex.org/W6634232107","https://openalex.org/W6787104050","https://openalex.org/W6800751262","https://openalex.org/W6804154756","https://openalex.org/W6810527279","https://openalex.org/W6810653034","https://openalex.org/W6811387395","https://openalex.org/W6839163910"],"related_works":["https://openalex.org/W182025740","https://openalex.org/W1809817947","https://openalex.org/W118585533","https://openalex.org/W151642146","https://openalex.org/W2149348622","https://openalex.org/W1971309227","https://openalex.org/W2168375594","https://openalex.org/W2396044781","https://openalex.org/W4288267738","https://openalex.org/W2964413124"],"abstract_inverted_index":{"Lying":[0],"in":[1,27],"the":[2,94,145,166],"cross-section":[3],"of":[4,16,109],"computer":[5],"vision":[6,11],"and":[7,19,34,71,79,136,154,162],"natural":[8],"language":[9,12,95],"processing,":[10],"models":[13,24,57,81],"are":[14,25,68,82,89],"capable":[15],"processing":[17],"images":[18,111],"text":[20,30],"at":[21],"once.":[22],"These":[23],"helpful":[26],"various":[28],"tasks:":[29],"generation":[31],"from":[32,118],"image":[33,69,176],"vice":[35],"versa,":[36],"image-text":[37,103],"retrieval,":[38],"or":[39],"visual":[40,72,158],"navigation.":[41],"Besides":[42],"building":[43],"a":[44,48,51,100],"model":[45,104],"trained":[46],"on":[47,144,165],"dataset":[49,108,147,168],"for":[50,62,86],"task,":[52],"people":[53],"also":[54],"study":[55],"general-purpose":[56,102],"to":[58,120,124],"utilize":[59],"many":[60],"datasets":[61,78],"multitasks.":[63],"Their":[64],"two":[65],"primary":[66],"applications":[67],"captioning":[70,177],"question":[73,159],"answering.":[74],"For":[75],"English,":[76],"large":[77],"foundation":[80],"already":[83],"abundant.":[84],"However,":[85],"Vietnamese,":[87],"they":[88],"still":[90],"limited.":[91],"To":[92],"expand":[93],"range,":[96],"this":[97],"work":[98],"proposes":[99],"pretrained":[101],"named":[105],"VisualRoBERTa.":[106,126],"A":[107],"600k":[110],"with":[112,148,169],"captions":[113],"(translated":[114],"MS":[115],"COCO":[116],"2017":[117],"English":[119],"Vietnamese)":[121],"is":[122,130],"introduced":[123],"pretrain":[125],"The":[127],"model\u2019s":[128],"architecture":[129],"built":[131],"using":[132],"Convolutional":[133],"Neural":[134],"Network":[135],"Transformer":[137],"blocks.":[138],"Fine-tuning":[139],"VisualRoBERTa":[140],"shows":[141],"promising":[142],"results":[143],"ViVQA":[146],"34.49%":[149],"accuracy,":[150],"0.4173":[151],"BLEU":[152,171],"4,":[153,172],"0.4390":[155],"RougeL":[156,174],"(in":[157,175],"answering":[160],"task),":[161],"best":[163],"outcomes":[164],"sViIC":[167],"0.6685":[170],"0.6320":[173],"task).":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
