{"id":"https://openalex.org/W2969897437","doi":"https://doi.org/10.1109/tmm.2019.2935678","title":"Frame Augmented Alternating Attention Network for Video Question Answering","display_name":"Frame Augmented Alternating Attention Network for Video Question Answering","publication_year":2019,"publication_date":"2019-08-23","ids":{"openalex":"https://openalex.org/W2969897437","doi":"https://doi.org/10.1109/tmm.2019.2935678","mag":"2969897437"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2935678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2935678","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/A5082131901","display_name":"Wenqiao Zhang","orcid":"https://orcid.org/0000-0002-5988-7609"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqiao Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627570","display_name":"Yanpeng Cao","orcid":"https://orcid.org/0000-0002-3052-4820"},"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":"Yanpeng Cao","raw_affiliation_strings":["School of Mechanical Engineering, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085955762","display_name":"Shiliang Pu","orcid":"https://orcid.org/0000-0001-5269-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiliang Pu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"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/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082131901"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":3.7452,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.94714395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"22","issue":"4","first_page":"1032","last_page":"1041"},"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":0.996399998664856,"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":0.9961000084877014,"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":0.8911287784576416},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6068505048751831},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5648220181465149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5598282814025879},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5489941835403442},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5485679507255554},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5022597312927246},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.49743011593818665},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4842814803123474},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4529196619987488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8911287784576416},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6068505048751831},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5648220181465149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598282814025879},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5489941835403442},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5485679507255554},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5022597312927246},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.49743011593818665},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4842814803123474},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4529196619987488},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2935678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2935678","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":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G240262592","display_name":null,"funder_award_id":"51605428","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5526867466","display_name":null,"funder_award_id":"U1611461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6605900608","display_name":null,"funder_award_id":"61751209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8967210090","display_name":null,"funder_award_id":"SQ2018AAA010010","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"}],"funders":[{"id":"https://openalex.org/F4320312071","display_name":"Ministry of Education, Libya","ror":"https://ror.org/02w030k33"},{"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/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1518233497","https://openalex.org/W1522734439","https://openalex.org/W1575833922","https://openalex.org/W1586939924","https://openalex.org/W1686810756","https://openalex.org/W1793121960","https://openalex.org/W1933349210","https://openalex.org/W1965963232","https://openalex.org/W2013822448","https://openalex.org/W2026012689","https://openalex.org/W2112193096","https://openalex.org/W2164290393","https://openalex.org/W2166348853","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2402144811","https://openalex.org/W2402268235","https://openalex.org/W2406288882","https://openalex.org/W2425121537","https://openalex.org/W2460852148","https://openalex.org/W2463565445","https://openalex.org/W2520610372","https://openalex.org/W2527089194","https://openalex.org/W2549699157","https://openalex.org/W2573426660","https://openalex.org/W2590526842","https://openalex.org/W2593722617","https://openalex.org/W2606982687","https://openalex.org/W2737435850","https://openalex.org/W2737766105","https://openalex.org/W2747623286","https://openalex.org/W2765716052","https://openalex.org/W2766690867","https://openalex.org/W2798786641","https://openalex.org/W2951008357","https://openalex.org/W2953384591","https://openalex.org/W2963150162","https://openalex.org/W2963191264","https://openalex.org/W2963560969","https://openalex.org/W2963954913","https://openalex.org/W2964022527","https://openalex.org/W2964220823","https://openalex.org/W3099768435","https://openalex.org/W3124951096","https://openalex.org/W6630875275","https://openalex.org/W6634232107","https://openalex.org/W6637373629","https://openalex.org/W6638318767","https://openalex.org/W6684090549","https://openalex.org/W6713098461","https://openalex.org/W6713134421","https://openalex.org/W6713482972","https://openalex.org/W6719057275","https://openalex.org/W6740863234","https://openalex.org/W6746311623"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Vision":[0],"and":[1,10,26,116,138,152,190],"language":[2,24],"understanding":[3,17],"is":[4,31],"one":[5],"of":[6,81,114,119,150],"the":[7,44,112,141,156,161,170,191,197],"most":[8],"fundamental":[9],"challenging":[11,34],"problems":[12],"in":[13,89,140,143],"Multimedia":[14],"Intelligence.":[15],"Simultaneously":[16],"video":[18,136,151,178],"actions":[19],"with":[20,101],"a":[21,73,106,117,125],"related":[22],"natural":[23],"question,":[25,153],"further":[27,154],"produces":[28],"accurate":[29],"answer":[30],"even":[32],"more":[33],"since":[35],"it":[36],"requires":[37],"joint":[38,148],"modeling":[39],"information":[40,104],"across":[41],"modality.":[42],"In":[43,93,121],"past":[45],"few":[46],"years,":[47],"some":[48],"studies":[49,184],"begin":[50],"to":[51,71,159],"attack":[52],"this":[53,94],"problem":[54],"by":[55,105],"utilizing":[56],"attention":[57,64,69,128,193],"enhanced":[58],"deep":[59,157],"neural":[60],"networks.":[61],"However,":[62],"simple":[63],"mechanisms":[65],"such":[66],"as":[67],"unidirectional":[68],"fail":[70],"yield":[72],"better":[74,147],"mapping":[75],"between":[76,164],"different":[77],"modalities.":[78,166],"Moreover,":[79],"none":[80],"these":[82],"Video":[83,172],"QA":[84,173],"models":[85,174],"explore":[86],"high-level":[87],"semantics":[88],"augmented":[90,97],"video-frame":[91],"level.":[92],"paper,":[95],"we":[96,123],"each":[98],"frame":[99,134],"representation":[100],"its":[102],"context":[103],"novel":[107,126],"feature":[108,188],"extractor":[109,189],"that":[110,186],"combines":[111],"advantages":[113],"Resnet":[115],"variant":[118],"C3D.":[120],"addition,":[122],"proposed":[124],"alternating":[127,192],"network":[129],"which":[130],"can":[131,195],"alternately":[132],"attend":[133],"regions,":[135],"frames":[137],"words":[139],"question":[142,179],"multi-turns.":[144],"This":[145],"yields":[146],"representations":[149],"help":[155],"model":[158],"discover":[160],"deeper":[162],"relationship":[163],"two":[165,176],"Our":[167],"method":[168],"outperforms":[169],"state-of-the-art":[171],"on":[175],"existing":[177],"answering":[180],"datasets.":[181],"Further":[182],"ablation":[183],"proved":[185],"our":[187],"mechanism":[194],"improve":[196],"performance":[198],"jointly.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
