{"id":"https://openalex.org/W4317418596","doi":"https://doi.org/10.1109/gcce56475.2022.10014385","title":"A Multimodal Interpretable Visual Question Answering Model Introducing Image Caption Processor","display_name":"A Multimodal Interpretable Visual Question Answering Model Introducing Image Caption Processor","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4317418596","doi":"https://doi.org/10.1109/gcce56475.2022.10014385"},"language":"en","primary_location":{"id":"doi:10.1109/gcce56475.2022.10014385","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce56475.2022.10014385","pdf_url":null,"source":{"id":"https://openalex.org/S4363607800","display_name":"2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044028436","display_name":"He Zhu","orcid":"https://orcid.org/0000-0001-9022-6158"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"He Zhu","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology","Graduate School of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology","Faculty of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology","Faculty of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology","Faculty of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"777","last_page":"778"},"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":0.9919000267982483,"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":0.9912999868392944,"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":0.849017322063446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8165292739868164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6277143359184265},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6259381771087646},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.586578369140625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49710896611213684},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45897263288497925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3910529613494873},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3740975558757782},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33121436834335327},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10768279433250427}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.849017322063446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165292739868164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6277143359184265},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6259381771087646},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.586578369140625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49710896611213684},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45897263288497925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3910529613494873},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3740975558757782},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33121436834335327},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10768279433250427}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce56475.2022.10014385","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce56475.2022.10014385","pdf_url":null,"source":{"id":"https://openalex.org/S4363607800","display_name":"2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2963609017","https://openalex.org/W3105391665","https://openalex.org/W3161801106","https://openalex.org/W4313046229"],"related_works":["https://openalex.org/W2805599431","https://openalex.org/W2961085424","https://openalex.org/W1891287906","https://openalex.org/W2361152157","https://openalex.org/W207304934","https://openalex.org/W2161229648","https://openalex.org/W2993674027","https://openalex.org/W2130228941","https://openalex.org/W4377703168","https://openalex.org/W1560657467"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"multimodal":[4],"interpretable":[5],"visual":[6],"question":[7],"answering":[8],"(VQA)":[9],"model":[10,63],"to":[11,48,78],"solve":[12],"the":[13,19,30,34,50,54,66,71,79],"lack":[14],"of":[15,18,53],"overall":[16],"understanding":[17],"previous":[20,35],"models,":[21],"which":[22],"is":[23],"caused":[24],"by":[25],"focusing":[26],"too":[27],"much":[28],"on":[29],"question.":[31],"Compared":[32],"with":[33,37],"models":[36],"only":[38],"image":[39,45],"reference,":[40],"we":[41],"newly":[42],"introduce":[43],"an":[44],"caption":[46],"processor":[47],"improve":[49],"prediction":[51],"process":[52],"VQA":[55],"model.":[56],"The":[57],"experimental":[58],"results":[59],"show":[60],"that":[61],"our":[62],"can":[64],"generate":[65],"answers":[67],"more":[68,74],"accurately":[69],"and":[70,76],"explanations":[72],"are":[73],"reasonable":[75],"closer":[77],"truth":[80],"than":[81],"some":[82],"state-of-art":[83],"methods.":[84]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}