{"id":"https://openalex.org/W3026441479","doi":"https://doi.org/10.1109/tmm.2020.2995278","title":"Self-Adaptive Neural Module Transformer for Visual Question Answering","display_name":"Self-Adaptive Neural Module Transformer for Visual Question Answering","publication_year":2020,"publication_date":"2020-05-18","ids":{"openalex":"https://openalex.org/W3026441479","doi":"https://doi.org/10.1109/tmm.2020.2995278","mag":"3026441479"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2020.2995278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2995278","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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/A5073939097","display_name":"Huasong Zhong","orcid":"https://orcid.org/0000-0001-7172-0556"},"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":true,"raw_author_name":"Huasong Zhong","raw_affiliation_strings":["Department of DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770061","display_name":"Jingyuan Chen","orcid":"https://orcid.org/0000-0001-5833-436X"},"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":"Jingyuan Chen","raw_affiliation_strings":["Department of DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022877637","display_name":"Chen Shen","orcid":"https://orcid.org/0000-0002-7534-0830"},"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":"Chen Shen","raw_affiliation_strings":["Department of DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079865276","display_name":"Jianqiang Huang","orcid":"https://orcid.org/0000-0001-5735-2910"},"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":"Jianqiang Huang","raw_affiliation_strings":["Department of DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024965898","display_name":"Xian\u2010Sheng Hua","orcid":"https://orcid.org/0000-0002-8232-5049"},"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":"Xian-Sheng Hua","raw_affiliation_strings":["Department of DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5073939097"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":4.5918,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.95862741,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"23","issue":null,"first_page":"1264","last_page":"1273"},"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":0.9965999722480774,"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":0.9932000041007996,"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":0.8490381240844727},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7471928596496582},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7027966380119324},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6199691295623779},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5583049058914185},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5450341105461121},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4865097403526306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4832106828689575},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4696827530860901},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.460559219121933},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42487218976020813},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4222196340560913},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4130741059780121},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32078349590301514},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30564573407173157},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20367968082427979},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16098350286483765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490381240844727},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7471928596496582},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7027966380119324},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6199691295623779},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5583049058914185},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5450341105461121},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4865097403526306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4832106828689575},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4696827530860901},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.460559219121933},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42487218976020813},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4222196340560913},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4130741059780121},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32078349590301514},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30564573407173157},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20367968082427979},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16098350286483765},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2020.2995278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2995278","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1518233497","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2013822448","https://openalex.org/W2064675550","https://openalex.org/W2130942839","https://openalex.org/W2147800946","https://openalex.org/W2168894214","https://openalex.org/W2194775991","https://openalex.org/W2471094925","https://openalex.org/W2520610372","https://openalex.org/W2527089194","https://openalex.org/W2529436507","https://openalex.org/W2549699157","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2590526842","https://openalex.org/W2594990650","https://openalex.org/W2745461083","https://openalex.org/W2760103357","https://openalex.org/W2793546384","https://openalex.org/W2883104598","https://openalex.org/W2895836448","https://openalex.org/W2922438466","https://openalex.org/W2962716332","https://openalex.org/W2963223524","https://openalex.org/W2963224792","https://openalex.org/W2963403868","https://openalex.org/W2963606038","https://openalex.org/W2963890019","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964118342","https://openalex.org/W2964138343","https://openalex.org/W2966683369","https://openalex.org/W2969897437","https://openalex.org/W3099849198","https://openalex.org/W4297749157","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6679436768","https://openalex.org/W6684665197","https://openalex.org/W6739901393","https://openalex.org/W6740674931","https://openalex.org/W6748270630"],"related_works":["https://openalex.org/W2275988210","https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W2293063786","https://openalex.org/W4200629926"],"abstract_inverted_index":{"Vision":[0],"and":[1,10,42,78,109,147,211,222,235],"language":[2,50],"understanding":[3],"is":[4,21],"one":[5],"of":[6,95,142,205],"the":[7,32,48,69,72,79,82,92,121,143,148,159,163,184,187,203,206,226],"most":[8],"fundamental":[9],"difficult":[11],"tasks":[12],"in":[13,120],"Multimedia":[14],"Intelligence.":[15],"Simultaneously":[16],"Visual":[17],"Question":[18],"Answering":[19],"(VQA)":[20],"even":[22],"more":[23],"challenging":[24,216],"since":[25],"it":[26],"requires":[27],"complex":[28],"reasoning":[29,122,181,192],"steps":[30],"to":[31,102,107,172,194,240],"correct":[33],"answer.":[34],"To":[35],"achieve":[36],"this,":[37],"Neural":[38,134],"Module":[39,135],"Network":[40],"(NMN)":[41],"its":[43,212],"variants":[44,213],"rely":[45],"on":[46,214],"parsing":[47],"natural":[49],"question":[51,73,96,144,165,175],"into":[52,74],"a":[53,57,65,75,129,168],"module":[54,117,171],"layout":[55,149,197],"(i.e.,":[56,98,113],"problem-solving":[58],"program).":[59],"In":[60,124],"particular,":[61],"this":[62,125],"process":[63],"follows":[64],"feedforward":[66],"encoder-decoder":[67,90],"pipeline:":[68],"encoder":[70],"embeds":[71],"static":[76],"vector":[77],"decoder":[80],"generates":[81],"layout.":[83],"However,":[84],"we":[85,99,114,127,157],"argue":[86],"that":[87],"such":[88],"conventional":[89],"neglects":[91],"dynamic":[93,174],"nature":[94],"comprehension":[97],"should":[100,115],"attend":[101],"different":[103],"words":[104],"from":[105,190],"step":[106,193],"step)":[108],"per-module":[110],"intermediate":[111,153,160,188],"results":[112,161,189],"discard":[116],"performing":[118],"badly)":[119],"steps.":[123,182],"paper,":[126],"present":[128],"novel":[130,169],"NMN,":[131],"called":[132],"Self-Adaptive":[133],"Transformer":[136],"(SANMT),":[137],"which":[138,178],"adaptively":[139],"adjusts":[140],"both":[141],"feature":[145,176],"encoding":[146],"decoding":[150],"by":[151,167],"considering":[152],"Q&A":[154],"results.":[155],"Specifically,":[156],"encode":[158],"with":[162,238],"given":[164],"features":[166],"transformer":[170,185],"generate":[173],"embedding":[177],"evolves":[179],"over":[180,209,229],"Besides,":[183],"utilizes":[186],"each":[191],"guide":[195],"subsequent":[196],"arrangement.":[198],"Extensive":[199],"experimental":[200],"evaluations":[201],"demonstrate":[202],"superiority":[204],"proposed":[207],"SANMT":[208],"NMN":[210,230],"four":[215],"benchmarks,":[217],"including":[218],"CLEVR,":[219],"CLEVR-CoGenT,":[220],"VQAv1.0,":[221],"VQAv2.0":[223],"(on":[224],"average":[225],"relative":[227],"improvement":[228],"are":[231],"1.5,":[232],"2.3,":[233],"0.7":[234],"0.5":[236],"points":[237],"respect":[239],"accuracy).":[241]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}