{"id":"https://openalex.org/W2561296180","doi":"https://doi.org/10.24963/ijcai.2017/592","title":"Automatic Generation of Grounded Visual Questions","display_name":"Automatic Generation of Grounded Visual Questions","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2561296180","doi":"https://doi.org/10.24963/ijcai.2017/592","mag":"2561296180"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/592","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/592","pdf_url":"https://www.ijcai.org/proceedings/2017/0592.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0592.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100669780","display_name":"Shijie Zhang","orcid":"https://orcid.org/0000-0001-5394-3991"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008486397","display_name":"Lizhen Qu","orcid":"https://orcid.org/0000-0002-7764-431X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lizhen Qu","raw_affiliation_strings":["Australian National University","DATA61","Australian National University; DATA61"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"DATA61","institution_ids":[]},{"raw_affiliation_string":"Australian National University; DATA61","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003277535","display_name":"Shaodi You","orcid":"https://orcid.org/0000-0001-8973-645X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shaodi You","raw_affiliation_strings":["Australian National University","DATA61","Australian National University; DATA61"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"DATA61","institution_ids":[]},{"raw_affiliation_string":"Australian National University; DATA61","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013188461","display_name":"Zhenglu Yang","orcid":"https://orcid.org/0000-0001-9528-965X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenglu Yang","raw_affiliation_strings":["College of Computer and Control Engineering, Nankai University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Control Engineering, Nankai University, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086311840","display_name":"Jiawan Zhang","orcid":"https://orcid.org/0000-0002-0667-6744"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawan Zhang","raw_affiliation_strings":["The School of Computer Software, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The School of Computer Software, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3081,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.94121569,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4235","last_page":"4243"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9927999973297119,"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":0.9897000193595886,"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/correctness","display_name":"Correctness","score":0.8484318256378174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7968580722808838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6217505931854248},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6025504469871521},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.5828759670257568},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.5064393281936646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5018596649169922},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4776110351085663},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4469105005264282},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44474634528160095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3346686363220215},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1292893886566162},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.06169551610946655}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8484318256378174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968580722808838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6217505931854248},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6025504469871521},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.5828759670257568},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.5064393281936646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5018596649169922},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4776110351085663},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4469105005264282},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44474634528160095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3346686363220215},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1292893886566162},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.06169551610946655},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/592","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/592","pdf_url":"https://www.ijcai.org/proceedings/2017/0592.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/592","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/592","pdf_url":"https://www.ijcai.org/proceedings/2017/0592.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2493969831","display_name":null,"funder_award_id":"U1636116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G731925894","display_name":null,"funder_award_id":"11431006,","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2561296180.pdf","grobid_xml":"https://content.openalex.org/works/W2561296180.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W62621907","https://openalex.org/W68733909","https://openalex.org/W102708294","https://openalex.org/W627986001","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1524229024","https://openalex.org/W1525961042","https://openalex.org/W1575833922","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1801721664","https://openalex.org/W1847088711","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1934041838","https://openalex.org/W1983927101","https://openalex.org/W2048343491","https://openalex.org/W2097117768","https://openalex.org/W2106624428","https://openalex.org/W2122180654","https://openalex.org/W2123301721","https://openalex.org/W2125436662","https://openalex.org/W2142192571","https://openalex.org/W2148721079","https://openalex.org/W2149172860","https://openalex.org/W2151035455","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2181691731","https://openalex.org/W2250539671","https://openalex.org/W2251673953","https://openalex.org/W2277195237","https://openalex.org/W2302963717","https://openalex.org/W2962749469","https://openalex.org/W2963758027","https://openalex.org/W4239072543","https://openalex.org/W4241645538","https://openalex.org/W4298392976"],"related_works":["https://openalex.org/W1546533203","https://openalex.org/W2054080977","https://openalex.org/W2168627904","https://openalex.org/W1511554945","https://openalex.org/W2515552481","https://openalex.org/W2015439768","https://openalex.org/W4361008414","https://openalex.org/W1570348318","https://openalex.org/W4396854307","https://openalex.org/W2015444353"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,68],"propose":[4,69],"the":[5,43,60,66,89,98,105,122],"first":[6],"model":[7,71,82,120],"to":[8,11,32,52],"be":[9],"able":[10],"generate":[12,53],"visually":[13,75],"grounded":[14,76],"questions":[15,34,55,77,106],"with":[16,56,78,132],"diverse":[17],"types":[18,58],"for":[19,59],"a":[20,70,93,133],"single":[21],"image.":[22],"Visual":[23],"question":[24,101],"generation":[25],"is":[26],"an":[27],"emerging":[28],"topic":[29],"which":[30],"aims":[31],"ask":[33],"in":[35,107,125],"natural":[36],"language":[37],"based":[38],"on":[39,112],"visual":[40,62],"input.":[41,63],"To":[42,64],"best":[44],"of":[45,127],"our":[46,119],"knowledge,":[47],"it":[48],"lacks":[49],"automatic":[50],"methods":[51],"meaningful":[54],"various":[57],"same":[61],"circumvent":[65],"problem,":[67],"that":[72,118],"automatically":[73],"generates":[74,104],"varying":[79],"types.":[80],"Our":[81],"takes":[83],"as":[84],"input":[85],"both":[86,128],"images":[87],"and":[88,103,130],"captions":[90],"generated":[91],"by":[92],"dense":[94],"caption":[95],"model,":[96],"samples":[97],"most":[99],"probable":[100],"types,":[102],"sequel.":[108],"The":[109],"experimental":[110],"results":[111],"two":[113],"real":[114],"world":[115],"datasets":[116],"show":[117],"outperforms":[121],"strongest":[123],"baseline":[124],"terms":[126],"correctness":[129],"diversity":[131],"wide":[134],"margin.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}