{"id":"https://openalex.org/W4386597256","doi":"https://doi.org/10.1109/icip49359.2023.10222423","title":"Interpretable Visual Question Answering Referring to Outside Knowledge","display_name":"Interpretable Visual Question Answering Referring to Outside Knowledge","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386597256","doi":"https://doi.org/10.1109/icip49359.2023.10222423"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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,Japan","Graduate School of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, Japan","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,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","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,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","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,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","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":"2140","last_page":"2144"},"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":0.9894000291824341,"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":0.9890999794006348,"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":0.8484916090965271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7776426076889038},{"id":"https://openalex.org/keywords/rationality","display_name":"Rationality","score":0.7269025444984436},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.679924488067627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6323619484901428},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.550740659236908},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.47899195551872253},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.47075751423835754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46782368421554565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42172789573669434},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3239792585372925},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.08261367678642273}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8484916090965271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7776426076889038},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.7269025444984436},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.679924488067627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6323619484901428},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.550740659236908},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.47899195551872253},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47075751423835754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46782368421554565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42172789573669434},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3239792585372925},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.08261367678642273},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2080133951","https://openalex.org/W2101105183","https://openalex.org/W2150824314","https://openalex.org/W2506483933","https://openalex.org/W2600463316","https://openalex.org/W2896457183","https://openalex.org/W2952122856","https://openalex.org/W2963609017","https://openalex.org/W2973009097","https://openalex.org/W2998702515","https://openalex.org/W3009635072","https://openalex.org/W3094897602","https://openalex.org/W3099700870","https://openalex.org/W3105391665","https://openalex.org/W3161801106","https://openalex.org/W4226321975","https://openalex.org/W4229042118","https://openalex.org/W4313046229","https://openalex.org/W4317418596","https://openalex.org/W4318718936","https://openalex.org/W4320458302","https://openalex.org/W4379879090","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6755207826","https://openalex.org/W6791353385","https://openalex.org/W6811013733","https://openalex.org/W6811072154","https://openalex.org/W6849177959","https://openalex.org/W6850204008"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2147241511","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W3090872036","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952","https://openalex.org/W4287868219"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,36],"novel":[3],"multimodal":[4,111],"interpretable":[5,105],"VQA":[6],"model":[7,52,109,125],"that":[8,25,123],"can":[9,26,126],"answer":[10,131],"the":[11,45,48,51,61,88,94,115],"question":[12,107],"more":[13],"accurately":[14],"and":[15,29,59,82,133],"generate":[16,27,65],"diverse":[17],"explanations.":[18],"Although":[19],"researchers":[20],"have":[21,41],"proposed":[22,75],"several":[23],"methods":[24,40,129],"human-readable":[28],"fine-grained":[30],"natural":[31],"language":[32],"sentences":[33],"to":[34,55,63,86,93,102,113],"explain":[35],"model\u2019s":[37],"decision,":[38],"these":[39],"focused":[42],"solely":[43],"on":[44],"information":[46,57,78,91],"in":[47],"image.":[49],"Ideally,":[50],"should":[53],"refer":[54],"various":[56],"inside":[58],"outside":[60,80],"image":[62,84],"correctly":[64],"explanations,":[66],"just":[67],"as":[68],"we":[69],"use":[70],"background":[71],"knowledge":[72,81],"daily.":[73],"The":[74,96],"method":[76],"incorporates":[77],"from":[79],"multiple":[83],"captions":[85],"increase":[87],"diversity":[89],"of":[90,98,117],"available":[92],"model.":[95],"contribution":[97],"this":[99],"paper":[100],"is":[101],"construct":[103],"an":[104],"visual":[106],"answering":[108],"using":[110],"inputs":[112],"improve":[114],"rationality":[116],"generated":[118],"results.":[119],"Experimental":[120],"results":[121],"show":[122],"our":[124],"outperform":[127],"state-of-the-art":[128],"regarding":[130],"accuracy":[132],"explanation":[134],"rationality.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}