{"id":"https://openalex.org/W2949686305","doi":"https://doi.org/10.1145/3323873.3325044","title":"Stacked Self-Attention Networks for Visual Question Answering","display_name":"Stacked Self-Attention Networks for Visual Question Answering","publication_year":2019,"publication_date":"2019-06-05","ids":{"openalex":"https://openalex.org/W2949686305","doi":"https://doi.org/10.1145/3323873.3325044","mag":"2949686305"},"language":"en","primary_location":{"id":"doi:10.1145/3323873.3325044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3323873.3325044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","raw_type":"proceedings-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/A5101792110","display_name":"Qiang Sun","orcid":"https://orcid.org/0000-0002-2877-8960"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qiang Sun","raw_affiliation_strings":["Fundan University & ZheJiang Xin ZaiLing Technology Co. LTD, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fundan University & ZheJiang Xin ZaiLing Technology Co. LTD, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fundan University & ZheJiang Xin ZaiLing Technology Co. LTD, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fundan University & ZheJiang Xin ZaiLing Technology Co. LTD, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101792110"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3159,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.84315699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"211"},"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":0.9944000244140625,"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":0.9929999709129333,"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":0.8571808338165283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8390252590179443},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7544357776641846},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6775389909744263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6244568228721619},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6241957545280457},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6081550717353821},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5799246430397034},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5205410718917847},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4525066316127777},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42526185512542725},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41894787549972534}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8571808338165283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390252590179443},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7544357776641846},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6775389909744263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6244568228721619},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6241957545280457},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6081550717353821},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5799246430397034},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5205410718917847},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4525066316127777},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42526185512542725},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41894787549972534},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3323873.3325044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3323873.3325044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2190656909","https://openalex.org/W2532034655","https://openalex.org/W2546696630","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2892259963","https://openalex.org/W2962749469","https://openalex.org/W2962933067","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963477107","https://openalex.org/W2963672682","https://openalex.org/W2963954913","https://openalex.org/W2964138343"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Given":[0],"a":[1,18,45,76],"photograph,":[2],"the":[3,26,34,50,57,63,69,81,86,98,106,113],"task":[4],"of":[5,29,37],"Visual":[6],"Question":[7],"Answering":[8],"(VQA)":[9],"requires":[10],"joint":[11],"image":[12],"and":[13,31,56,111],"language":[14],"understanding":[15],"to":[16,71,95],"answer":[17],"question.":[19],"It":[20],"is":[21,89,103],"challenging":[22],"in":[23,91],"effectively":[24],"extracting":[25],"visual":[27,54],"representation":[28],"images,":[30],"efficiently":[32],"embedding":[33,60],"textual":[35],"sentences":[36],"questions.":[38],"To":[39],"address":[40],"these":[41],"challenges,":[42],"we":[43],"propose":[44],"VQA":[46,108],"model":[47,70,88,102],"that":[48],"utilizes":[49],"stacked":[51,64],"self-attention":[52,65],"for":[53],"understanding,":[55],"BERT-based":[58],"question":[59,99],"model.":[61],"Particularly,":[62],"mechanism":[66],"proposed":[67],"enables":[68],"not":[72],"only":[73],"focus":[74],"on":[75,105],"simple":[77],"object":[78],"but":[79],"also":[80],"relations":[82],"between":[83],"objects.":[84],"Furthermore,":[85],"BERT":[87],"learned":[90],"an":[92],"end-to-end":[93],"manner":[94],"better":[96],"embed":[97],"sentences.":[100],"Our":[101],"validated":[104],"well-known":[107],"v2.0":[109],"dataset,":[110],"achieves":[112],"state-of-the-art":[114],"results.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}