{"id":"https://openalex.org/W3208343573","doi":"https://doi.org/10.1109/iccvw54120.2021.00353","title":"Visual Question Answering with Textual Representations for Images","display_name":"Visual Question Answering with Textual Representations for Images","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3208343573","doi":"https://doi.org/10.1109/iccvw54120.2021.00353","mag":"3208343573"},"language":"en","primary_location":{"id":"doi:10.1109/iccvw54120.2021.00353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw54120.2021.00353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","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/A5103137644","display_name":"Yusuke Hirota","orcid":"https://orcid.org/0000-0001-7466-7690"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Hirota","raw_affiliation_strings":["Osaka University"],"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028370193","display_name":"Noa Garc\u00eda","orcid":"https://orcid.org/0000-0002-9200-6359"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noa Garcia","raw_affiliation_strings":["Osaka University"],"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035903147","display_name":"Mayu Otani","orcid":"https://orcid.org/0000-0001-9923-2669"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mayu Otani","raw_affiliation_strings":["CyberAgent, Inc"],"affiliations":[{"raw_affiliation_string":"CyberAgent, Inc","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065649079","display_name":"Yuta Nakashima","orcid":"https://orcid.org/0000-0001-8000-3567"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Nakashima","raw_affiliation_strings":["Osaka University"],"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050838950","display_name":"Ittetsu Taniguchi","orcid":"https://orcid.org/0000-0002-7843-5907"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ittetsu Taniguchi","raw_affiliation_strings":["Osaka University"],"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061693379","display_name":"Takao Onoye","orcid":"https://orcid.org/0000-0002-1894-2448"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Onoye","raw_affiliation_strings":["Osaka University"],"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103137644"],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":0.5764,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68915033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3147","last_page":"3150"},"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":0.9947999715805054,"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":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8616438508033752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7768526077270508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.664451003074646},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6188861727714539},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6134301424026489},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5241377949714661},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4906822443008423},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43361443281173706},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4112064838409424},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06413578987121582}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8616438508033752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768526077270508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.664451003074646},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6188861727714539},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6134301424026489},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5241377949714661},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4906822443008423},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43361443281173706},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4112064838409424},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06413578987121582},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw54120.2021.00353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw54120.2021.00353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"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":27,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2745461083","https://openalex.org/W2885380450","https://openalex.org/W2916723116","https://openalex.org/W2962858109","https://openalex.org/W2963521239","https://openalex.org/W2965373594","https://openalex.org/W2968124245","https://openalex.org/W2970019270","https://openalex.org/W2971296908","https://openalex.org/W2990397898","https://openalex.org/W3004349648","https://openalex.org/W3035517717","https://openalex.org/W3095670406","https://openalex.org/W3104788521","https://openalex.org/W4288286281","https://openalex.org/W4295253143","https://openalex.org/W6639102338","https://openalex.org/W6639432524","https://openalex.org/W6751097180","https://openalex.org/W6752083267","https://openalex.org/W6765591853","https://openalex.org/W6766673545","https://openalex.org/W6767279747"],"related_works":["https://openalex.org/W2805599431","https://openalex.org/W2361152157","https://openalex.org/W2351286801","https://openalex.org/W2356380379","https://openalex.org/W1594455022","https://openalex.org/W2357241418","https://openalex.org/W207304934","https://openalex.org/W4377703168","https://openalex.org/W15319282","https://openalex.org/W1560657467"],"abstract_inverted_index":{"How":[0],"far":[1],"can":[2],"we":[3,48],"go":[4],"with":[5,52],"textual":[6,73],"representations":[7,74],"for":[8,75],"understanding":[9,77],"pictures?":[10],"Deep":[11],"visual":[12,28,35],"features":[13,36],"extracted":[14],"by":[15],"object":[16],"recognition":[17],"models":[18],"are":[19],"prevailing":[20],"used":[21],"in":[22,27,44,78],"multiple":[23],"tasks,":[24],"and":[25],"especially":[26],"question":[29],"answering":[30],"(VQA).":[31],"However,":[32],"conventional":[33],"deep":[34],"may":[37,59],"struggle":[38],"to":[39,63],"convey":[40],"all":[41],"the":[42,70,79],"details":[43],"an":[45,61],"image":[46,76],"as":[47],"humans":[49],"do.":[50],"Mean-while,":[51],"recent":[53],"language":[54],"models\u2019":[55],"progress,":[56],"descriptive":[57],"text":[58],"be":[60],"alternative":[62],"this":[64],"problem.":[65],"This":[66],"paper":[67],"delves":[68],"into":[69],"effectiveness":[71],"of":[72,82],"specific":[80],"context":[81],"VQA.":[83]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}