{"id":"https://openalex.org/W2905524945","doi":"https://doi.org/10.1609/aaai.v33i01.33019324","title":"Dynamic Capsule Attention for Visual Question Answering","display_name":"Dynamic Capsule Attention for Visual Question Answering","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2905524945","doi":"https://doi.org/10.1609/aaai.v33i01.33019324","mag":"2905524945"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33019324","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019324","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4970/4843","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4970/4843","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091531008","display_name":"Yiyi Zhou","orcid":"https://orcid.org/0000-0002-5110-4526"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyi Zhou","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066326238","display_name":"Jinsong Su","orcid":"https://orcid.org/0000-0001-5606-7122"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Su","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070983714","display_name":"Weiqiu Chen","orcid":"https://orcid.org/0000-0003-0655-3303"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqiu Chen","raw_affiliation_strings":["Xiamen Univserity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen Univserity","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.196,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.92140699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"33","issue":"01","first_page":"9324","last_page":"9331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9884999990463257,"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":0.9771999716758728,"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/closed-captioning","display_name":"Closed captioning","score":0.8018090724945068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806644439697266},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7723814845085144},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.65951007604599},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5708178281784058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5058250427246094},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4723314642906189},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4314056932926178},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.424888014793396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4196038246154785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.328734815120697},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1782398819923401}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8018090724945068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806644439697266},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7723814845085144},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.65951007604599},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5708178281784058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058250427246094},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4723314642906189},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4314056932926178},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.424888014793396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4196038246154785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.328734815120697},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1782398819923401},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33019324","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019324","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4970/4843","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4970","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33019324","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019324","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4970/4843","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2905524945.pdf","grobid_xml":"https://content.openalex.org/works/W2905524945.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1484210532","https://openalex.org/W1514535095","https://openalex.org/W1575833922","https://openalex.org/W1686810756","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W2115595010","https://openalex.org/W2133564696","https://openalex.org/W2171810632","https://openalex.org/W2176212817","https://openalex.org/W2194775991","https://openalex.org/W2293453011","https://openalex.org/W2463565445","https://openalex.org/W2560730294","https://openalex.org/W2613718673","https://openalex.org/W2621571501","https://openalex.org/W2744822616","https://openalex.org/W2745461083","https://openalex.org/W2949197413","https://openalex.org/W2951527505","https://openalex.org/W2963066927","https://openalex.org/W2963150162","https://openalex.org/W2963398599","https://openalex.org/W2963656855","https://openalex.org/W2963703618","https://openalex.org/W2963954913","https://openalex.org/W3016211260","https://openalex.org/W4385245566","https://openalex.org/W6634232107","https://openalex.org/W6640773114","https://openalex.org/W6677032036","https://openalex.org/W6687483927","https://openalex.org/W6692647644","https://openalex.org/W6743446608"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"In":[0,68],"visual":[1,104],"question":[2,19,30],"answering":[3],"(VQA),":[4],"recent":[5,97],"advances":[6],"have":[7],"well":[8],"advocated":[9],"the":[10,18,21,26,29,41,50,56,96,110,118,126,140,160,193,200],"use":[11],"of":[12,28,52,99,169,203,214],"attention":[13,37,86,111,119,163],"mechanism":[14],"to":[15,20,39,59,77,138,159,171,192],"precisely":[16],"link":[17],"potential":[22],"answer":[23],"areas.":[24],"As":[25],"difficulty":[27],"increases,":[31],"more":[32,143],"VQA":[33,151,195],"models":[34],"adopt":[35],"multiple":[36],"layers":[38],"capture":[40],"deeper":[42],"visual-linguistic":[43],"correlation.":[44],"But":[45],"a":[46,223],"negative":[47],"consequence":[48],"is":[49,220],"explosion":[51],"parameters,":[53,184],"which":[54,116],"makes":[55],"model":[57,141],"vulnerable":[58],"over-fitting,":[60],"especially":[61],"when":[62],"limited":[63],"training":[64],"examples":[65],"are":[66],"given.":[67],"this":[69,78],"paper,":[70],"we":[71,205],"propose":[72],"an":[73],"extremely":[74],"compact":[75],"alternative":[76],"static":[79],"multi-layer":[80,162],"architecture":[81],"towards":[82],"accurate":[83],"yet":[84],"efficient":[85],"modeling,":[87],"termed":[88],"as":[89,106],"Dynamic":[90],"Capsule":[91,100],"Attention":[92],"(CapsAtt).":[93],"Inspired":[94],"by":[95,121],"work":[98],"Network,":[101],"CapsAtt":[102,132,147,165],"treats":[103],"features":[105],"capsules":[107],"and":[108,128,156,174],"obtains":[109],"output":[112,129],"via":[113],"dynamic":[114],"routing,":[115],"updates":[117],"weights":[120],"calculating":[122],"coupling":[123],"coefficients":[124],"between":[125],"underlying":[127],"capsules.":[130],"Meanwhile,":[131],"also":[133,187,206],"discards":[134],"redundant":[135],"projection":[136],"matrices":[137],"make":[139],"much":[142,182],"compact.":[144],"We":[145],"quantify":[146],"on":[148,176,209],"three":[149,177],"benchmark":[150],"datasets,":[152,178],"i.e.,":[153],"COCO-QA,":[154],"VQA1.0":[155],"VQA2.0.":[157],"Compared":[158],"traditional":[161],"model,":[164],"achieves":[166],"significant":[167],"improvements":[168],"up":[170],"4.1%,":[172],"5.2%":[173],"2.2%":[175],"respectively.":[179],"Moreover,":[180],"with":[181,222],"fewer":[183],"our":[185],"approach":[186],"yields":[188],"competitive":[189],"results":[190],"compared":[191],"latest":[194],"models.":[196],"To":[197],"further":[198],"verify":[199],"generalization":[201],"ability":[202],"CapsAtt,":[204],"deploy":[207],"it":[208],"another":[210],"challenging":[211],"multi-modal":[212],"task":[213],"image":[215],"captioning,":[216],"where":[217],"state-of-the-art":[218],"performance":[219],"achieved":[221],"simple":[224],"network":[225],"structure.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}