{"id":"https://openalex.org/W3027790991","doi":"https://doi.org/10.1109/tcsvt.2020.2995959","title":"Long-Term Video Question Answering via Multimodal Hierarchical Memory Attentive Networks","display_name":"Long-Term Video Question Answering via Multimodal Hierarchical Memory Attentive Networks","publication_year":2020,"publication_date":"2020-05-20","ids":{"openalex":"https://openalex.org/W3027790991","doi":"https://doi.org/10.1109/tcsvt.2020.2995959","mag":"3027790991"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2020.2995959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.2995959","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5048112344","display_name":"Ting Yu","orcid":"https://orcid.org/0000-0001-6918-3157"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]},{"id":"https://openalex.org/I90727586","display_name":"Zhejiang University of Finance and Economics","ror":"https://ror.org/055vj5234","country_code":"CN","type":"education","lineage":["https://openalex.org/I90727586"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ting Yu","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","School of Information, Zhejiang University of Finance and Economics Dongfang College, Haining, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"School of Information, Zhejiang University of Finance and Economics Dongfang College, Haining, China","institution_ids":["https://openalex.org/I90727586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393506","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-7252-5047"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Noah\u2019s Ark Laboratory, Huawei, China","Noah's Ark Laboratory, Huawei, China"],"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Laboratory, Huawei, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Noah's Ark Laboratory, Huawei, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048112344"],"corresponding_institution_ids":["https://openalex.org/I50760025","https://openalex.org/I90727586"],"apc_list":null,"apc_paid":null,"fwci":4.03,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.95041884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"31","issue":"3","first_page":"931","last_page":"944"},"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":0.9955000281333923,"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":0.9937000274658203,"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":0.7940549850463867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887147665023804},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6180559992790222},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5135017037391663},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.47308188676834106},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.45377853512763977},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.42806294560432434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41779959201812744},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33086931705474854},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.21391740441322327},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09330600500106812}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7940549850463867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887147665023804},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6180559992790222},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5135017037391663},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.47308188676834106},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.45377853512763977},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.42806294560432434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41779959201812744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33086931705474854},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.21391740441322327},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09330600500106812},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2020.2995959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.2995959","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2133050864","display_name":null,"funder_award_id":"61972119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5054529767","display_name":null,"funder_award_id":"61702143","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":null,"funder_award_id":"61836002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7572920239","display_name":null,"funder_award_id":"61806063","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1793121960","https://openalex.org/W2064675550","https://openalex.org/W2131494463","https://openalex.org/W2142192571","https://openalex.org/W2151498684","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2293453011","https://openalex.org/W2597958930","https://openalex.org/W2606982687","https://openalex.org/W2613718673","https://openalex.org/W2735159761","https://openalex.org/W2740759433","https://openalex.org/W2741859754","https://openalex.org/W2741903908","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2755876276","https://openalex.org/W2765716052","https://openalex.org/W2796354110","https://openalex.org/W2808124938","https://openalex.org/W2808181286","https://openalex.org/W2885380450","https://openalex.org/W2904452845","https://openalex.org/W2908056713","https://openalex.org/W2950527759","https://openalex.org/W2951008357","https://openalex.org/W2952620298","https://openalex.org/W2953016680","https://openalex.org/W2954199749","https://openalex.org/W2962677524","https://openalex.org/W2962938145","https://openalex.org/W2962949233","https://openalex.org/W2963383024","https://openalex.org/W2963579811","https://openalex.org/W2963676207","https://openalex.org/W2964022527","https://openalex.org/W2964091467","https://openalex.org/W2964199361","https://openalex.org/W2964220823","https://openalex.org/W2964312929","https://openalex.org/W2964345214","https://openalex.org/W2966683369","https://openalex.org/W2969127500","https://openalex.org/W2970401203","https://openalex.org/W2972113750","https://openalex.org/W2974161034","https://openalex.org/W2982139784","https://openalex.org/W3023993913","https://openalex.org/W3105758476","https://openalex.org/W4294551350","https://openalex.org/W4298392976","https://openalex.org/W4303633609","https://openalex.org/W6607333740","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6638318767","https://openalex.org/W6679844565","https://openalex.org/W6682086655","https://openalex.org/W6684821475","https://openalex.org/W6685189238","https://openalex.org/W6694395031","https://openalex.org/W6697449767","https://openalex.org/W6730666313","https://openalex.org/W6742999658","https://openalex.org/W6743068658","https://openalex.org/W6748579893","https://openalex.org/W6766222867"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912"],"abstract_inverted_index":{"Long-term":[0],"Video":[1],"Question":[2],"Answering":[3],"plays":[4],"an":[5,41,141],"essential":[6],"role":[7],"in":[8,156],"visual":[9,37],"information":[10],"retrieval,":[11],"which":[12],"aims":[13],"at":[14,54,126],"generating":[15],"natural":[16],"language":[17],"answers":[18],"to":[19,45,51,113,145,160,204],"discretionary":[20],"free-form":[21],"questions":[22,120],"about":[23],"the":[24,31,47,52,60,78,89,95,131,167,187,206,209],"referenced":[25],"long-term":[26,196],"video.":[27],"Rather":[28],"than":[29],"remember":[30],"video":[32,124,153,174],"as":[33,108,140],"a":[34,109,127,157],"sequence":[35],"of":[36,119],"content,":[38],"humans":[39],"have":[40],"innate":[42],"cognitive":[43],"ability":[44],"identify":[46],"critical":[48,65],"moments":[49,66,118],"related":[50],"question":[53,162,175],"first":[55],"glance,":[56],"then":[57],"tie":[58],"together":[59],"specific":[61],"evidence":[62,155],"around":[63],"these":[64],"for":[67,195],"further":[68],"analysis":[69],"and":[70,94,116,121,181],"reasoning.":[71],"Motivated":[72],"by":[73],"this":[74],"intuition,":[75],"we":[76],"propose":[77],"multimodal":[79,98,134],"hierarchical":[80],"memory":[81,87,92,99,105,135],"attentive":[82,100,136],"networks":[83],"with":[84,150],"two":[85],"heterogeneous":[86],"subnetworks:":[88],"top":[90,103],"guided":[91,104],"network":[93,106,137],"bottom":[96,132,154],"enhanced":[97,133],"network.":[101],"The":[102],"serves":[107],"shallow":[110],"inference":[111],"engine":[112,144],"pick":[114],"relevant":[115],"informative":[117],"obtain":[122],"salient":[123],"content":[125],"coarse-grained":[128],"level.":[129],"Subsequently,":[130],"is":[138],"designed":[139],"in-depth":[142],"reasoning":[143],"perform":[146],"more":[147],"accurate":[148],"attention":[149],"cues":[151],"from":[152],"fine-grained":[158],"level":[159],"enhance":[161],"answering":[163,176],"quality.":[164],"We":[165],"evaluate":[166],"proposed":[168,188,210],"method":[169],"on":[170],"three":[171],"publicly":[172],"available":[173],"benchmarks,":[177],"namely":[178],"ActivityNet-QA,":[179],"MSRVTT-QA,":[180],"MSVD-QA.":[182],"Experimental":[183],"results":[184],"demonstrate":[185],"that":[186],"approach":[189],"significantly":[190],"outperforms":[191],"other":[192],"state-of-the-art":[193],"methods":[194],"videos.":[197],"Extensive":[198],"ablation":[199],"studies":[200],"are":[201],"carried":[202],"out":[203],"explore":[205],"reasons":[207],"behind":[208],"model's":[211],"effectiveness.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}