{"id":"https://openalex.org/W4416508284","doi":"https://doi.org/10.1007/978-981-95-4963-4_30","title":"RPR-MCAoAN: A Transformer-Based Co-attention Network with\u00a0Relative Positional Representations for\u00a0Visual Question Answering","display_name":"RPR-MCAoAN: A Transformer-Based Co-attention Network with\u00a0Relative Positional Representations for\u00a0Visual Question Answering","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W4416508284","doi":"https://doi.org/10.1007/978-981-95-4963-4_30"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-4963-4_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-4963-4_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5066544761","display_name":"Pham Nhan","orcid":"https://orcid.org/0009-0000-3339-8041"},"institutions":[{"id":"https://openalex.org/I4210148201","display_name":"Ho Chi Minh City University of Technology and Education","ror":"https://ror.org/05hzn5427","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210148201"]},{"id":"https://openalex.org/I4210104442","display_name":"Ho Chi Minh City University of Education","ror":"https://ror.org/01cs0jg44","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210104442"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Pham Hoai Nhan","raw_affiliation_strings":["Faculty of Information Technology, Ho Chi Minh City University of Education, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Ho Chi Minh City University of Education, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210104442","https://openalex.org/I4210148201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120465718","display_name":"Thai Gia Bao","orcid":"https://orcid.org/0009-0007-3512-4977"},"institutions":[{"id":"https://openalex.org/I4210148201","display_name":"Ho Chi Minh City University of Technology and Education","ror":"https://ror.org/05hzn5427","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210148201"]},{"id":"https://openalex.org/I4210104442","display_name":"Ho Chi Minh City University of Education","ror":"https://ror.org/01cs0jg44","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210104442"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thai Gia Bao","raw_affiliation_strings":["Faculty of Information Technology, Ho Chi Minh City University of Education, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Ho Chi Minh City University of Education, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210104442","https://openalex.org/I4210148201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101739586","display_name":"Nguy\u1ec5n Minh H\u1ea3i","orcid":"https://orcid.org/0000-0002-4329-7428"},"institutions":[{"id":"https://openalex.org/I4210104442","display_name":"Ho Chi Minh City University of Education","ror":"https://ror.org/01cs0jg44","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210104442"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Minh Hai","raw_affiliation_strings":["Faculty of Physics, Ho Chi Minh City University of Education, Ho Chi Minh, Vietnam"],"affiliations":[{"raw_affiliation_string":"Faculty of Physics, Ho Chi Minh City University of Education, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210104442"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066544761"],"corresponding_institution_ids":["https://openalex.org/I4210104442","https://openalex.org/I4210148201"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77212411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"363","last_page":"374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9939000010490417,"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":0.9939000010490417,"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/T10028","display_name":"Topic Modeling","score":0.0010999999940395355,"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":0.0006000000284984708,"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/question-answering","display_name":"Question answering","score":0.8669000267982483},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.583899974822998},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5267000198364258},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4984999895095825},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.36469998955726624},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.361299991607666},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35929998755455017},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8924999833106995},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8669000267982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6757000088691711},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48899999260902405},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-4963-4_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-4963-4_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2963925437","https://openalex.org/W2963954913","https://openalex.org/W2964345214","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2986670728","https://openalex.org/W3128587100","https://openalex.org/W3132185473","https://openalex.org/W3186187670","https://openalex.org/W3203701986","https://openalex.org/W4225166070","https://openalex.org/W4312554250","https://openalex.org/W4312784228","https://openalex.org/W4385573030","https://openalex.org/W4385637197","https://openalex.org/W4386703217","https://openalex.org/W4387777447","https://openalex.org/W4393152856"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-28T16:06:27.173445","created_date":"2025-11-23T00:00:00"}
