{"id":"https://openalex.org/W4312554250","doi":"https://doi.org/10.1109/tmm.2022.3216770","title":"Positional Attention Guided Transformer-Like Architecture for Visual Question Answering","display_name":"Positional Attention Guided Transformer-Like Architecture for Visual Question Answering","publication_year":2022,"publication_date":"2022-11-03","ids":{"openalex":"https://openalex.org/W4312554250","doi":"https://doi.org/10.1109/tmm.2022.3216770"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3216770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3216770","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/A5014555076","display_name":"Aihua Mao","orcid":"https://orcid.org/0000-0001-6861-9414"},"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":"Aihua Mao","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6861-9414","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101561407","display_name":"Yang Zhi","orcid":"https://orcid.org/0000-0002-9768-2356"},"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":"Zhi Yang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9768-2356","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004174106","display_name":"Ken Lin","orcid":null},"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":"Ken Lin","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075858925","display_name":"Jun Xuan","orcid":"https://orcid.org/0000-0002-7975-7852"},"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":"Jun Xuan","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008076279","display_name":"Yong\u2010Jin Liu","orcid":"https://orcid.org/0000-0001-5774-1916"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-Jin Liu","raw_affiliation_strings":["BNRist, Department of Computer Science and Technology, Tsinghua University, and MOE-Key Laboratory of Pervasive Computing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5774-1916","affiliations":[{"raw_affiliation_string":"BNRist, Department of Computer Science and Technology, Tsinghua University, and MOE-Key Laboratory of Pervasive Computing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":2.9002,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.92609814,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"6997","last_page":"7009"},"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":0.9987000226974487,"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":0.9980999827384949,"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":0.8466728329658508},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7938083410263062},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7659481167793274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5864430665969849},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5131036043167114},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42992669343948364},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4107477366924286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39891284704208374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3417345881462097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466728329658508},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7938083410263062},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7659481167793274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5864430665969849},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5131036043167114},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42992669343948364},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4107477366924286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39891284704208374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3417345881462097},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3216770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3216770","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":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1736198338","display_name":null,"funder_award_id":"61725204","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1575833922","https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2787119853","https://openalex.org/W2807941860","https://openalex.org/W2896457183","https://openalex.org/W2896902935","https://openalex.org/W2962884579","https://openalex.org/W2962964995","https://openalex.org/W2963521239","https://openalex.org/W2963560969","https://openalex.org/W2963925437","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964080601","https://openalex.org/W2964118342","https://openalex.org/W2964138017","https://openalex.org/W2964345214","https://openalex.org/W2966683369","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2995971510","https://openalex.org/W2997531716","https://openalex.org/W2998699904","https://openalex.org/W3004349648","https://openalex.org/W3026441479","https://openalex.org/W3034336960","https://openalex.org/W3034787499","https://openalex.org/W3034837210","https://openalex.org/W3087975588","https://openalex.org/W3100786684","https://openalex.org/W3122515622","https://openalex.org/W3128587100","https://openalex.org/W3138516171","https://openalex.org/W3186187670","https://openalex.org/W3205539018","https://openalex.org/W3206171352","https://openalex.org/W4285723986","https://openalex.org/W4288089799","https://openalex.org/W4297779827","https://openalex.org/W4298392976","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6634232107","https://openalex.org/W6637373629","https://openalex.org/W6682086655","https://openalex.org/W6719057275","https://openalex.org/W6739901393","https://openalex.org/W6748581942","https://openalex.org/W6749537441","https://openalex.org/W6752083267","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6769627184","https://openalex.org/W6771497439","https://openalex.org/W6772111226","https://openalex.org/W6772203101","https://openalex.org/W6779902714","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4381058564","https://openalex.org/W3204607391","https://openalex.org/W3049463507","https://openalex.org/W2964413124","https://openalex.org/W2936497627","https://openalex.org/W4388937922","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287598411","https://openalex.org/W4287826556"],"abstract_inverted_index":{"Transformer":[0,33],"architectures":[1],"have":[2],"recently":[3],"been":[4],"introduced":[5,134],"into":[6,122],"the":[7,93,131,162,178,186],"field":[8],"of":[9,19,48,55,180,188],"visual":[10,94,153],"question":[11],"answering":[12],"(VQA),":[13],"due":[14],"to":[15,65,102,144],"their":[16],"powerful":[17],"capabilities":[18],"information":[20,47,54,89,101,110,133],"extraction":[21],"and":[22,35,52,91,95,98,108,116,165,183,193],"fusion.":[23],"However,":[24],"existing":[25],"Transformer-like":[26,82,125],"models,":[27,40],"including":[28],"models":[29,164],"using":[30],"a":[31,77,123],"single":[32,124],"structure":[34],"large-scale":[36],"pre-training":[37],"generic":[38],"visual-linguistic":[39],"do":[41],"not":[42],"fully":[43],"utilize":[44],"both":[45],"positional":[46,53,79,88,119,132],"words":[49],"in":[50,57,62,68,106,135],"questions":[51],"objects":[56],"images,":[58],"which":[59,84,147],"are":[60],"shown":[61],"this":[63,73,100],"paper":[64],"be":[66],"crucial":[67],"VQA":[69,190,194],"tasks.":[70],"To":[71],"address":[72],"challenge,":[74],"we":[75,114],"propose":[76],"novel":[78],"attention":[80,120],"guided":[81],"architecture,":[83],"can":[85,138],"adaptively":[86,139],"extracts":[87],"within":[90],"across":[92],"language":[96],"modalities,":[97],"use":[99],"guide":[103],"high-level":[104],"interactions":[105],"inter-":[107],"intra-modality":[109,136],"flows.":[111],"In":[112],"particular,":[113],"design":[115],"assemble":[117],"three":[118],"modules":[121],"model":[126,160,176],"MCAN.":[127],"We":[128],"show":[129],"that":[130,158],"interaction":[137,142],"modulate":[140],"inter-modality":[141],"according":[143],"different":[145],"inputs,":[146],"plays":[148],"an":[149],"important":[150],"role":[151],"for":[152],"reasoning.":[154],"Experimental":[155],"results":[156],"demonstrate":[157],"our":[159,175],"outperforms":[161],"state-of-the-art":[163],"is":[166],"particularly":[167],"good":[168],"at":[169],"handling":[170],"object":[171],"counting":[172],"questions.":[173],"Overall,":[174],"achieves":[177],"accuracy":[179],"70.10%,":[181],"71.27%,":[182],"71.52%":[184],"on":[185],"datasets":[187],"COCO-QA,":[189],"v1.0":[191],"test-std":[192],"v2.0":[195],"test-std,":[196],"respectively.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}