{"id":"https://openalex.org/W2741903908","doi":"https://doi.org/10.24963/ijcai.2017/492","title":"Video Question Answering via Hierarchical Spatio-Temporal Attention Networks","display_name":"Video Question Answering via Hierarchical Spatio-Temporal Attention Networks","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2741903908","doi":"https://doi.org/10.24963/ijcai.2017/492","mag":"2741903908"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/492","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/492","pdf_url":"https://www.ijcai.org/proceedings/2017/0492.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0492.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["College of Computer Science, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002378639","display_name":"Qifan Yang","orcid":"https://orcid.org/0000-0003-1791-985X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qifan Yang","raw_affiliation_strings":["College of Computer Science, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013345","display_name":"Xiaofei He","orcid":"https://orcid.org/0009-0001-9107-2354"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei He","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["College of Computer Science, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079260216"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":5.5464,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.9751035,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3518","last_page":"3524"},"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":0.995199978351593,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9840999841690063,"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/question-answering","display_name":"Question answering","score":0.9153223633766174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.845651388168335},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7194278836250305},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6257555484771729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5078375935554504},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4872680902481079},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4829351603984833},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4689815640449524},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42242830991744995},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30386555194854736}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9153223633766174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845651388168335},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7194278836250305},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6257555484771729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5078375935554504},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4872680902481079},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4829351603984833},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4689815640449524},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42242830991744995},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30386555194854736},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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:10.24963/ijcai.2017/492","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/492","pdf_url":"https://www.ijcai.org/proceedings/2017/0492.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/492","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/492","pdf_url":"https://www.ijcai.org/proceedings/2017/0492.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1022706131","display_name":null,"funder_award_id":"61602405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1045833371","display_name":null,"funder_award_id":"2016QNA5015","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1828425977","display_name":null,"funder_award_id":"973 Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5616582905","display_name":null,"funder_award_id":"2013CB336500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5853313636","display_name":null,"funder_award_id":"Knowledge","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6194230105","display_name":null,"funder_award_id":"2013CB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7129907147","display_name":null,"funder_award_id":"(973 Program","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8951484681","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327609","display_name":"China Knowledge Centre for Engineering Sciences and Technology","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741903908.pdf","grobid_xml":"https://content.openalex.org/works/W2741903908.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1531374185","https://openalex.org/W1586939924","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1895641373","https://openalex.org/W1924770834","https://openalex.org/W2078784669","https://openalex.org/W2131494463","https://openalex.org/W2136480620","https://openalex.org/W2202226326","https://openalex.org/W2288052783","https://openalex.org/W2293453011","https://openalex.org/W2412393473","https://openalex.org/W2421253313","https://openalex.org/W2463565445","https://openalex.org/W2553418567","https://openalex.org/W2563399268","https://openalex.org/W2578606145","https://openalex.org/W2950577311","https://openalex.org/W2951008357","https://openalex.org/W2951619830","https://openalex.org/W2963191264","https://openalex.org/W2963293463","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2964138343","https://openalex.org/W4298033729","https://openalex.org/W4298392976","https://openalex.org/W4299341000"],"related_works":["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/W4200629926","https://openalex.org/W4220955952","https://openalex.org/W4226470070"],"abstract_inverted_index":{"Open-ended":[0],"video":[1,22,47,56,67,94,115,122],"question":[2,32,48,68,116,123],"answering":[3,33,49,69,124],"is":[4],"a":[5,120],"challenging":[6],"problem":[7,64],"in":[8],"visual":[9,31],"information":[10],"retrieval,":[11],"which":[12,41],"automatically":[13],"generates":[14],"the":[15,20,26,29,38,52,63,71,81,88,92,98,104,130],"natural":[16],"language":[17],"answer":[18],"from":[19,70],"referenced":[21],"content":[23],"according":[24,96],"to":[25,46,51,97],"question.":[27,100],"However,":[28],"existing":[30],"works":[34],"only":[35],"focus":[36],"on":[37],"static":[39],"image,":[40],"may":[42],"be":[43],"ineffectively":[44],"applied":[45],"due":[50],"temporal":[53],"dynamics":[54],"of":[55,65,73,91,132],"contents.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"consider":[62],"open-ended":[66,114],"viewpoint":[72],"spatio-temporal":[74,83],"attentional":[75],"encoder-decoder":[76,105],"learning":[77,87,106],"framework.":[78],"We":[79,101,118],"propose":[80],"hierarchical":[82],"attention":[84],"network":[85],"for":[86,113],"joint":[89],"representation":[90],"dynamic":[93],"contents":[95],"given":[99],"then":[102],"develop":[103],"method":[107],"with":[108],"reasoning":[109],"recurrent":[110],"neural":[111],"networks":[112],"answering.":[117],"construct":[119],"large-scale":[121],"dataset.":[125],"The":[126],"extensive":[127],"experiments":[128],"show":[129],"effectiveness":[131],"our":[133],"method.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}