{"id":"https://openalex.org/W4226465229","doi":"https://doi.org/10.1145/3572833","title":"Achieving Human Parity on Visual Question Answering","display_name":"Achieving Human Parity on Visual Question Answering","publication_year":2022,"publication_date":"2022-12-20","ids":{"openalex":"https://openalex.org/W4226465229","doi":"https://doi.org/10.1145/3572833"},"language":"en","primary_location":{"id":"doi:10.1145/3572833","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572833","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-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/A5100452477","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0003-4959-8878"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4959-8878","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haiyang Xu","orcid":"https://orcid.org/0000-0001-9442-5912"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Xu","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9442-5912","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734065","display_name":"Chenliang Li","orcid":"https://orcid.org/0000-0001-9077-3928"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenliang Li","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9077-3928","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junfeng Tian","orcid":"https://orcid.org/0000-0003-1759-3255"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Tian","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1759-3255","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081108106","display_name":"Bin Bi","orcid":"https://orcid.org/0000-0003-2207-9146"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Bi","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2207-9146","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602362","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-7028-9845"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7028-9845","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xianzhe Xu","orcid":"https://orcid.org/0000-0001-7498-1903"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianzhe Xu","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7498-1903","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329266","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0002-3835-7975"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3835-7975","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047856952","display_name":"Songfang Huang","orcid":"https://orcid.org/0000-0001-8084-0904"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songfang Huang","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8084-0904","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-3709-5053"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3709-5053","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101718341","display_name":"Luo Si","orcid":"https://orcid.org/0000-0002-3263-234X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo Si","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3263-234X","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069394608","display_name":"Rong Jin","orcid":"https://orcid.org/0000-0002-8797-4646"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Jin","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8797-4646","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0296381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":"3","first_page":"1","last_page":"40"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"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":0.9793000221252441,"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":0.7522001266479492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7340980768203735},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5966610908508301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5315026640892029},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5056014060974121},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.485231876373291},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.429179847240448},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4223722517490387},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4136020541191101},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35544490814208984},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3460255265235901},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08212506771087646}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7522001266479492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7340980768203735},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5966610908508301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315026640892029},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5056014060974121},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.485231876373291},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.429179847240448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4223722517490387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4136020541191101},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35544490814208984},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3460255265235901},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08212506771087646},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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:10.1145/3572833","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572833","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1966382373","https://openalex.org/W1979065383","https://openalex.org/W2028175314","https://openalex.org/W2071207147","https://openalex.org/W2106277773","https://openalex.org/W2108598243","https://openalex.org/W2150884987","https://openalex.org/W2171278097","https://openalex.org/W2257979135","https://openalex.org/W2277195237","https://openalex.org/W2388114291","https://openalex.org/W2412400526","https://openalex.org/W2463565445","https://openalex.org/W2563399268","https://openalex.org/W2581624817","https://openalex.org/W2613718673","https://openalex.org/W2740747242","https://openalex.org/W2799187742","https://openalex.org/W2886641317","https://openalex.org/W2889787757","https://openalex.org/W2896457183","https://openalex.org/W2899335602","https://openalex.org/W2923014074","https://openalex.org/W2947555604","https://openalex.org/W2953874899","https://openalex.org/W2954547017","https://openalex.org/W2965373594","https://openalex.org/W2966892770","https://openalex.org/W2969862959","https://openalex.org/W2969876226","https://openalex.org/W3007672467","https://openalex.org/W3014611590","https://openalex.org/W3018442911","https://openalex.org/W3020834808","https://openalex.org/W3033276647","https://openalex.org/W3035652667","https://openalex.org/W3116952214","https://openalex.org/W3118641406","https://openalex.org/W3119866685","https://openalex.org/W3126337491","https://openalex.org/W3126792443","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3155787390","https://openalex.org/W3164881641","https://openalex.org/W3171915994","https://openalex.org/W3179867916","https://openalex.org/W3182937942","https://openalex.org/W3193402170","https://openalex.org/W3207798279","https://openalex.org/W6718053083","https://openalex.org/W6721087566","https://openalex.org/W6736172710","https://openalex.org/W6761041305","https://openalex.org/W6772988795"],"related_works":["https://openalex.org/W10050918","https://openalex.org/W6789168","https://openalex.org/W7174772","https://openalex.org/W1195902","https://openalex.org/W15101074","https://openalex.org/W13360413","https://openalex.org/W15595896","https://openalex.org/W2923437","https://openalex.org/W24270","https://openalex.org/W2710505"],"abstract_inverted_index":{"The":[0],"Visual":[1],"Question":[2],"Answering":[3],"(VQA)":[4],"task":[5],"utilizes":[6],"both":[7],"visual":[8,103,139],"image":[9,108],"and":[10,50,119,167],"language":[11,51],"analysis":[12,168],"to":[13,20,70,89,158,171],"answer":[14],"a":[15,26,44,78,97,121],"textual":[16],"question":[17],"with":[18,30,115,125,141],"respect":[19],"an":[21,31,146],"image.":[22],"It":[23],"has":[24],"been":[25],"popular":[27],"research":[28,178],"topic":[29],"increasing":[32],"number":[33],"of":[34,48,55,61,94,138,153,165,175],"real-world":[35],"applications":[36],"in":[37,96,149],"the":[38,91,131,151,159,173,176],"last":[39],"decade.":[40],"This":[41],"paper":[42],"introduces":[43],"novel":[45],"hierarchical":[46,85],"integration":[47,124],"vision":[49],"AliceMind-MMU":[52],"(ALIbaba\u2019s":[53],"Collection":[54],"Encoder-decoders":[56],"from":[57],"Machine":[58],"IntelligeNce":[59],"lab":[60],"Damo":[62],"academy":[63],"-":[64],"MultiMedia":[65],"Understanding)":[66],",":[67],"which":[68],"leads":[69],"similar":[71],"or":[72],"even":[73],"slightly":[74],"better":[75],"results":[76],"than":[77],"human":[79,160],"being":[80],"does":[81],"on":[82],"VQA.":[83],"A":[84],"framework":[86],"is":[87],"designed":[88],"tackle":[90],"practical":[92],"problems":[93],"VQA":[95,133,155],"cascade":[98],"manner":[99],"including:":[100],"(1)":[101],"diverse":[102],"semantics":[104],"learning":[105],"for":[106,130],"comprehensive":[107],"content":[109],"understanding;":[110],"(2)":[111],"enhanced":[112],"multi-modal":[113],"pre-training":[114],"modality":[116],"adaptive":[117],"attention;":[118],"(3)":[120],"knowledge-guided":[122],"model":[123],"three":[126],"specialized":[127],"expert":[128],"modules":[129],"complex":[132],"task.":[134],"Treating":[135],"different":[136],"types":[137],"questions":[140],"corresponding":[142],"expertise":[143],"needed":[144],"plays":[145],"important":[147],"role":[148],"boosting":[150],"performance":[152],"our":[154],"architecture":[156],"up":[157],"level.":[161],"An":[162],"extensive":[163],"set":[164],"experiments":[166],"are":[169],"conducted":[170],"demonstrate":[172],"effectiveness":[174],"new":[177],"work.":[179]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2022-05-05T00:00:00"}