{"id":"https://openalex.org/W4399658739","doi":"https://doi.org/10.1145/3641584.3641770","title":"Visual Question Answering Model Based on Relationship graphs and Co-Attention","display_name":"Visual Question Answering Model Based on Relationship graphs and Co-Attention","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4399658739","doi":"https://doi.org/10.1145/3641584.3641770"},"language":"en","primary_location":{"id":"doi:10.1145/3641584.3641770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3641584.3641770","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3641584.3641770?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3641584.3641770?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016865114","display_name":"Wei Guan","orcid":"https://orcid.org/0000-0001-5832-2027"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Guan","raw_affiliation_strings":["Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090335004","display_name":"Xueli Yang","orcid":"https://orcid.org/0009-0000-1062-9193"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueli Yang","raw_affiliation_strings":["Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5099124640","display_name":"Li Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Ma","raw_affiliation_strings":["Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016865114"],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22829481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1237","last_page":"1242"},"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":0.9980999827384949,"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":0.9908000230789185,"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/question-answering","display_name":"Question answering","score":0.8243224620819092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5970812439918518},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.479495108127594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4291011095046997},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3768293857574463},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35219985246658325},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.1930217146873474},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09392738342285156}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8243224620819092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5970812439918518},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.479495108127594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4291011095046997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3768293857574463},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35219985246658325},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.1930217146873474},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09392738342285156},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641584.3641770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3641584.3641770","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3641584.3641770?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3641584.3641770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3641584.3641770","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3641584.3641770?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399658739.pdf","grobid_xml":"https://content.openalex.org/works/W4399658739.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2963938081","https://openalex.org/W2963954913","https://openalex.org/W3016211260"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"is":[3,16,128],"a":[4,52,70,97],"very":[5],"challenging":[6],"tasks":[7],"in":[8],"the":[9,22,30,38,41,74,77,80,84,87,93,103,106,131,135,140,143,146,156],"fiield":[10],"of":[11,40,86,145],"AI.":[12],"The":[13,126],"existing":[14,157],"model":[15,42,56,127,141,150],"not":[17],"accurate":[18],"enough":[19],"to":[20,44,114,122,151],"judge":[21],"relationship":[23,59],"between":[24,32,76,83],"problem":[25,33,78],"words,":[26],"image":[27,35],"objects":[28,85],"and":[29,34,61,79,82,89,134],"association":[31],"objects,":[36],"meanwhile,":[37],"interpretability":[39],"needs":[43],"be":[45,66],"improved.":[46],"In":[47],"response,":[48],"this":[49],"paper":[50],"proposes":[51],"visual":[53,147],"question":[54,148],"answering":[55,149],"based":[57],"on":[58,130],"graph":[60,72,95,98],"co-attention.":[62],"Relational":[63],"features":[64,108,119],"can":[65],"obtained":[67,107],"by":[68,90,102],"constructing":[69],"relational":[71,94],"using":[73,96,111],"relationships":[75],"image,":[81,88],"dynamically":[91],"updating":[92],"attention":[99,113],"network":[100],"guided":[101],"problem.":[104],"Then,":[105],"are":[109,120],"fused":[110],"co-":[112],"obtain":[115],"richer":[116],"features.Finally,":[117],"these":[118],"used":[121],"make":[123],"answer":[124],"prediction.":[125],"experimented":[129],"VQA2.0":[132],"dataset,":[133],"experimental":[136],"results":[137],"show":[138],"that":[139],"improved":[142],"accuracy":[144],"some":[152],"extent":[153],"compared":[154],"with":[155],"models.":[158]},"counts_by_year":[],"updated_date":"2026-03-08T06:56:09.383167","created_date":"2025-10-10T00:00:00"}