{"id":"https://openalex.org/W4304091788","doi":"https://doi.org/10.1145/3503161.3548387","title":"AI-VQA","display_name":"AI-VQA","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091788","doi":"https://doi.org/10.1145/3503161.3548387"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548387","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548387","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th 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/A5064453711","display_name":"Rengang Li","orcid":"https://orcid.org/0000-0002-4297-4335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rengang Li","raw_affiliation_strings":["Inspur (Beijing) Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur (Beijing) Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055434477","display_name":"Cong Xu","orcid":"https://orcid.org/0000-0002-9288-1743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Xu","raw_affiliation_strings":["Inspur (Beijing) Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur (Beijing) Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055656398","display_name":"Zhenhua Guo","orcid":"https://orcid.org/0000-0002-1303-6681"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Guo","raw_affiliation_strings":["Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017156592","display_name":"Baoyu Fan","orcid":"https://orcid.org/0009-0005-5223-6183"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoyu Fan","raw_affiliation_strings":["Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101549172","display_name":"Runze Zhang","orcid":"https://orcid.org/0009-0003-6318-3342"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Zhang","raw_affiliation_strings":["Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568187","display_name":"Yaqian Zhao","orcid":"https://orcid.org/0000-0002-9170-0090"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqian Zhao","raw_affiliation_strings":["Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074821242","display_name":"Weifeng Gong","orcid":"https://orcid.org/0009-0005-0213-8008"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Gong","raw_affiliation_strings":["Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043582248","display_name":"Endong Wang","orcid":"https://orcid.org/0000-0002-7715-0045"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Endong Wang","raw_affiliation_strings":["Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co., Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5274","last_page":"5282"},"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":0.9950000047683716,"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":0.9947999715805054,"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":0.8312289714813232},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7681601047515869},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5928127765655518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5687019228935242},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5189530849456787},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5145137310028076},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49668556451797485},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.47462236881256104},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47456079721450806},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.45866551995277405},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.45481622219085693},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4331362247467041},{"id":"https://openalex.org/keywords/literal","display_name":"Literal (mathematical logic)","score":0.4229484498500824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3872317671775818},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3870770037174225},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22956323623657227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312289714813232},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7681601047515869},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5928127765655518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5687019228935242},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5189530849456787},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5145137310028076},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49668556451797485},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.47462236881256104},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47456079721450806},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.45866551995277405},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.45481622219085693},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4331362247467041},{"id":"https://openalex.org/C2780882242","wikidata":"https://www.wikidata.org/wiki/Q14235582","display_name":"Literal (mathematical logic)","level":2,"score":0.4229484498500824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3872317671775818},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3870770037174225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22956323623657227},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548387","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548387","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G3178178310","display_name":null,"funder_award_id":"No.2021ZD0113000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1983927101","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2561715562","https://openalex.org/W2745461083","https://openalex.org/W2963115613","https://openalex.org/W2963150162","https://openalex.org/W2963518342","https://openalex.org/W2963521239","https://openalex.org/W2964002344","https://openalex.org/W2964279831","https://openalex.org/W2964303913","https://openalex.org/W2970641574","https://openalex.org/W3091588028","https://openalex.org/W3093407505","https://openalex.org/W3161801106","https://openalex.org/W3173220247","https://openalex.org/W3194523157","https://openalex.org/W3205346281","https://openalex.org/W3206082179","https://openalex.org/W3207204435","https://openalex.org/W3209108897","https://openalex.org/W4220667080","https://openalex.org/W4239019441","https://openalex.org/W6752083267"],"related_works":["https://openalex.org/W3134247745","https://openalex.org/W4226243593","https://openalex.org/W3172691639","https://openalex.org/W2963582704","https://openalex.org/W4403761773","https://openalex.org/W4401140950","https://openalex.org/W4297783004","https://openalex.org/W2914694625","https://openalex.org/W4400650325","https://openalex.org/W4287330440"],"abstract_inverted_index":{"Visual":[0,96,151],"Question":[1,97],"Answering":[2,98],"(VQA)":[3],"serves":[4],"as":[5,44],"a":[6,51,63,100,110,116,146,194,210,226],"proxy":[7],"for":[8,136,184],"evaluating":[9],"the":[10,41,71,76,107,129,133,141,177,182,189,202,206,223],"scene":[11,104],"understanding":[12,37,105],"of":[13,79,176],"an":[14,80,174],"intelligent":[15],"agent":[16,108],"by":[17,225],"answering":[18],"questions":[19,31,54,124],"about":[20],"images.":[21],"Most":[22],"VQA":[23],"benchmarks":[24],"to":[25,66,121,127],"date":[26],"are":[27],"focused":[28],"on":[29,70,150,188,209],"those":[30],"that":[32,55,199,218],"can":[33,200],"be":[34],"answered":[35],"through":[36],"visual":[38,47],"content":[39,78],"in":[40,131],"scene,":[42,72],"such":[43],"simple":[45],"counting,":[46],"attributes,":[48],"and":[49,82,153,164,204],"even":[50],"little":[52],"challenging":[53],"require":[56],"extra":[57],"encyclopedic":[58],"knowledge.":[59],"However,":[60],"humans":[61],"have":[62],"remarkable":[64],"capacity":[65],"reason":[67,207],"dynamic":[68],"interaction":[69,134,203],"which":[73,132],"is":[74],"beyond":[75],"literal":[77],"image":[81],"has":[83],"not":[84,118],"been":[85],"investigated":[86],"so":[87],"far.":[88],"In":[89],"this":[90,114],"paper,":[91],"we":[92,144,171,191],"propose":[93,193],"Agent":[94],"Interaction":[95],"(AI-VQA),":[99],"task":[101],"investigating":[102],"deep":[103],"if":[106],"takes":[109],"certain":[111],"action.":[112,142],"For":[113],"task,":[115],"model":[117],"only":[119],"needs":[120],"answer":[122,183],"action-related":[123],"but":[125],"also":[126,172],"locate":[128],"objects":[130],"occurs":[135],"guaranteeing":[137],"it":[138,167],"truly":[139],"comprehends":[140],"Accordingly,":[143],"make":[145,166],"new":[147],"dataset":[148],"based":[149,208],"Genome":[152],"ATOMIC":[154],"knowledge":[155,213],"graph,":[156],"including":[157],"more":[158],"than":[159],"19,000":[160],"manually":[161],"annotated":[162],"questions,":[163],"will":[165],"publicly":[168],"available.":[169],"Besides,":[170],"provide":[173],"annotation":[175],"reasoning":[178],"path":[179],"while":[180],"developing":[181],"each":[185],"question.":[186],"Based":[187],"dataset,":[190],"further":[192],"novel":[195],"method,":[196],"called":[197],"ARE,":[198],"comprehend":[201],"explain":[205],"given":[211],"event":[212],"base.":[214],"Experimental":[215],"results":[216],"show":[217],"our":[219],"proposed":[220],"method":[221],"outperforms":[222],"baseline":[224],"clear":[227],"margin.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-10-10T00:00:00"}