{"id":"https://openalex.org/W3206904785","doi":"https://doi.org/10.1145/3474085.3476969","title":"Multiple Objects-Aware Visual Question Generation","display_name":"Multiple Objects-Aware Visual Question Generation","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206904785","doi":"https://doi.org/10.1145/3474085.3476969","mag":"3206904785"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3476969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3476969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5049131355","display_name":"Jiayuan Xie","orcid":"https://orcid.org/0000-0002-6833-7879"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Xie","raw_affiliation_strings":["South China University of Technology & Ministry of Education, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology & Ministry of Education, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["South China University of Technology & Ministry of Education, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology & Ministry of Education, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061381102","display_name":"Qingbao Huang","orcid":"https://orcid.org/0000-0001-7691-347X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbao Huang","raw_affiliation_strings":["South China University of Technology, Ministry of Education, & Guangxi University, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Ministry of Education, & Guangxi University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I150807315","https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100453458","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0002-0437-0557"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["King's College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London, London, United Kingdom","institution_ids":["https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4546","last_page":"4554"},"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":0.991599977016449,"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":0.9900000095367432,"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/computer-science","display_name":"Computer science","score":0.8071504235267639},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7116971015930176},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.642138659954071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5770357251167297},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5629570484161377},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.560984194278717},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5426351428031921},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4869621694087982},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4731884002685547},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4638718366622925},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45626401901245117},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4208880364894867},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3234715461730957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.25708311796188354},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.22676408290863037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071504235267639},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7116971015930176},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.642138659954071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770357251167297},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5629570484161377},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.560984194278717},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5426351428031921},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4869621694087982},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4731884002685547},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4638718366622925},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45626401901245117},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4208880364894867},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3234715461730957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25708311796188354},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22676408290863037},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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":2,"locations":[{"id":"doi:10.1145/3474085.3476969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3476969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/f9754660-7264-462c-b5a1-ad8f2277385a","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/f9754660-7264-462c-b5a1-ad8f2277385a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xie, J, Cai, Y, Huang, Q & Wang, T 2021, Multiple Objects-Aware Visual Question Generation. in MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia. Proceedings of the 29th ACM International Conference on Multimedia, pp. 4546-4554, 29th ACM International Conference on Multimedia, MM 2021, Virtual, Online, China, 20/10/2021. https://doi.org/10.1145/3474085.3476969","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W627986001","https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2151035455","https://openalex.org/W2154652894","https://openalex.org/W2189070436","https://openalex.org/W2250539671","https://openalex.org/W2560730294","https://openalex.org/W2561296180","https://openalex.org/W2575842049","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2796070532","https://openalex.org/W2808021740","https://openalex.org/W2808336545","https://openalex.org/W2895088466","https://openalex.org/W2898071615","https://openalex.org/W2949130399","https://openalex.org/W2949218037","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2951619830","https://openalex.org/W2953106684","https://openalex.org/W2962749469","https://openalex.org/W2962943108","https://openalex.org/W2963051286","https://openalex.org/W2963087285","https://openalex.org/W2963187678","https://openalex.org/W2963351776","https://openalex.org/W2963954913","https://openalex.org/W2963976294","https://openalex.org/W2964015378","https://openalex.org/W2964065333","https://openalex.org/W2964121744","https://openalex.org/W2964324871","https://openalex.org/W3001952301","https://openalex.org/W3004349648","https://openalex.org/W3019023591","https://openalex.org/W3034787499","https://openalex.org/W3092692431"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W4392007279","https://openalex.org/W4387129494"],"abstract_inverted_index":{"Visual":[0],"question":[1],"generation":[2,83],"task":[3],"aims":[4],"to":[5,13,26,33,44,61,68,85,91,105,127,136,154,181],"generate":[6,34,62,95,159],"meaningful":[7],"questions":[8,63,160],"about":[9],"an":[10,31,49,92,113],"image":[11,32,114,149],"according":[12],"a":[14,35,38,80,102,131,177],"target":[15,28,39],"answer.":[16,73,129],"Existing":[17],"studies":[18],"mainly":[19],"focus":[20],"on":[21,53,186],"merely":[22],"one":[23,55],"object":[24,56,111],"related":[25,43,67,90,126,153],"the":[27,72,96,107,116,121,128,138,141,148,155,167,171,187,193,197],"answer":[29,40,93],"in":[30,48,112,147],"question.":[36,98],"However,":[37],"is":[41,134,174],"often":[42],"multiple":[45],"key":[46,88,122,142],"objects":[47,89,123,143,146],"image,":[50],"which":[51,157],"focuses":[52],"only":[54,66],"may":[57],"mislead":[58],"its":[59],"model":[60,84,195],"that":[64,124,150,161,192],"are":[65,125,151],"partial":[69],"fragments":[70],"of":[71],"To":[74],"address":[75],"this":[76],"problem,":[77],"we":[78],"propose":[79],"multi-objects":[81],"aware":[82],"capture":[86,106,137],"all":[87],"and":[94,115,118,144],"corresponding":[97],"We":[99],"first":[100],"introduce":[101],"co-attention":[103],"network":[104,133,173],"relationship":[108],"between":[109,140],"each":[110],"answer,":[117,156],"then":[119],"extract":[120],"Then,":[130],"graph":[132,172],"introduced":[135],"relationships":[139],"other":[145],"not":[152],"helps":[158],"involve":[162],"more":[163],"visual":[164],"content.":[165],"Finally,":[166],"learned":[168],"information":[169],"from":[170],"fed":[175],"into":[176],"standard":[178],"decoder":[179],"module":[180],"produce":[182],"questions.":[183],"Extensive":[184],"experiments":[185],"VQA":[188],"v2.0":[189],"dataset":[190],"show":[191],"proposed":[194],"outperforms":[196],"state-of-the-art":[198],"models.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}