{"id":"https://openalex.org/W3035419698","doi":"https://doi.org/10.24963/ijcai.2020/139","title":"Feature Augmented Memory with Global Attention Network for VideoQA","display_name":"Feature Augmented Memory with Global Attention Network for VideoQA","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035419698","doi":"https://doi.org/10.24963/ijcai.2020/139","mag":"3035419698"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/139","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/139","pdf_url":"https://www.ijcai.org/proceedings/2020/0139.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth 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/2020/0139.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066854056","display_name":"Jiayin Cai","orcid":"https://orcid.org/0009-0007-8903-212X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayin Cai","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School","Department of Computer Science and Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102906277","display_name":"Shi Cheng","orcid":"https://orcid.org/0000-0002-6942-8481"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Shi","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440326","display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-5374-7293"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021760829","display_name":"Yangyang Cheng","orcid":"https://orcid.org/0000-0003-4991-6610"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Cheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["ARC, Tencent PCG","Department of Computer Science and Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0557,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.89081582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"998","last_page":"1004"},"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":0.996999979019165,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.8493894338607788},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.740357518196106},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7086896300315857},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7086676359176636},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.6945865750312805},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.5647214651107788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5635437965393066},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.44054660201072693},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3671191930770874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3538975417613983},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3528631031513214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493894338607788},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.740357518196106},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7086896300315857},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7086676359176636},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.6945865750312805},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.5647214651107788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5635437965393066},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.44054660201072693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3671191930770874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3538975417613983},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3528631031513214},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/139","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/139","pdf_url":"https://www.ijcai.org/proceedings/2020/0139.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/139","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/139","pdf_url":"https://www.ijcai.org/proceedings/2020/0139.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4469221245","display_name":null,"funder_award_id":"U1833101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035419698.pdf","grobid_xml":"https://content.openalex.org/works/W3035419698.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2808181286","https://openalex.org/W2904291752","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2962949233","https://openalex.org/W2963091558","https://openalex.org/W2963293463","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3093895509","https://openalex.org/W3163481960","https://openalex.org/W2323394100","https://openalex.org/W280704926","https://openalex.org/W2476068070","https://openalex.org/W4323971310","https://openalex.org/W2893372175","https://openalex.org/W1972827106","https://openalex.org/W4385714117","https://openalex.org/W4312773091"],"abstract_inverted_index":{"Recently,":[0],"Recurrent":[1],"Neural":[2],"Network":[3],"(RNN)":[4],"based":[5,10],"methods":[6,11,28,48],"and":[7,82,118,129,136],"Self-Attention":[8],"(SA)":[9],"have":[12],"achieved":[13],"promising":[14],"performance":[15,164],"in":[16,89],"Video":[17],"Question":[18],"Answering":[19],"(VideoQA).":[20],"Despite":[21],"the":[22,32,38,42,52,55,78,97,101,113,134,140,144],"success":[23],"of":[24,41,54,80,116],"these":[25,67],"works,":[26],"RNN-based":[27],"tend":[29],"to":[30,37,59,86,111,139,148],"forget":[31],"global":[33,150],"semantic":[34,154],"contents":[35],"due":[36],"inherent":[39],"drawbacks":[40],"recurrent":[43],"units":[44],"themselves,":[45],"while":[46],"SA-based":[47],"cannot":[49],"precisely":[50],"capture":[51,149],"dependencies":[53],"local":[56],"neighborhood,":[57],"leading":[58],"insufficient":[60],"modeling":[61],"for":[62],"temporal":[63],"order.":[64],"To":[65],"tackle":[66],"problems,":[68],"we":[69],"propose":[70],"a":[71,90],"novel":[72],"VideoQA":[73,166],"framework":[74],"which":[75,120],"progressively":[76],"refines":[77],"representations":[79,99],"videos":[81],"questions":[83],"from":[84],"fine":[85],"coarse":[87],"grain":[88],"sequence-sensitive":[91],"manner.":[92],"Specifically,":[93],"our":[94,160],"model":[95],"improves":[96],"feature":[98],"via":[100],"following":[102],"two":[103,107],"steps:":[104],"(1)":[105],"introducing":[106],"fine-grained":[108],"feature-augmented":[109],"memories":[110],"strengthen":[112],"information":[114],"augmentation":[115],"video":[117],"text":[119],"can":[121],"improve":[122],"memory":[123,141],"capacity":[124],"by":[125],"memorizing":[126],"more":[127],"relevant":[128],"targeted":[130],"information.":[131],"(2)":[132],"appending":[133],"self-attention":[135],"co-attention":[137],"module":[138,145],"output":[142],"thus":[143],"is":[146],"able":[147],"interaction":[151],"between":[152],"high-level":[153],"informations.":[155],"Experimental":[156],"results":[157],"show":[158],"that":[159],"approach":[161],"achieves":[162],"state-of-the-art":[163],"on":[165],"benchmark":[167],"datasets.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}