{"id":"https://openalex.org/W3160451259","doi":"https://doi.org/10.1145/3460426.3463635","title":"Relation-aware Hierarchical Attention Framework for Video Question Answering","display_name":"Relation-aware Hierarchical Attention Framework for Video Question Answering","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3160451259","doi":"https://doi.org/10.1145/3460426.3463635","mag":"3160451259"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.06160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fangtao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fangtao Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ting Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Bai","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenyu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Cao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zihe Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihe Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenghao Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenghao Yan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.8739,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75353046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"164","last_page":"172"},"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":0.9973999857902527,"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":0.9972000122070312,"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":0.7452999949455261},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6446999907493591},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.546999990940094},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4903999865055084},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48190000653266907},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36730000376701355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8327999711036682},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7452999949455261},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6446999907493591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5540000200271606},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3695000112056732},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3460426.3463635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.06160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.06160","pdf_url":"https://arxiv.org/pdf/2105.06160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.06160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.06160","pdf_url":"https://arxiv.org/pdf/2105.06160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4437476954","display_name":null,"funder_award_id":"61972047","funder_id":"https://openalex.org/F4320334117","funder_display_name":"National Natural Science Foundation of China-Shenzhen Robotics Research Center Project"},{"id":"https://openalex.org/G7208197312","display_name":null,"funder_award_id":"2018YFC0831500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320334117","display_name":"National Natural Science Foundation of China-Shenzhen Robotics Research Center Project","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1651753422","https://openalex.org/W2113507809","https://openalex.org/W2161813894","https://openalex.org/W2250539671","https://openalex.org/W2565656701","https://openalex.org/W2605572715","https://openalex.org/W2606982687","https://openalex.org/W2787581402","https://openalex.org/W2890531016","https://openalex.org/W2916723116","https://openalex.org/W2935568096","https://openalex.org/W2962850006","https://openalex.org/W2962949233","https://openalex.org/W2963191264","https://openalex.org/W2963541336","https://openalex.org/W2963717374","https://openalex.org/W2964010806","https://openalex.org/W2964080601","https://openalex.org/W2964346351","https://openalex.org/W2965345045","https://openalex.org/W2997344006","https://openalex.org/W2997789966","https://openalex.org/W2998166190","https://openalex.org/W3004349648","https://openalex.org/W3023993913","https://openalex.org/W3034730770","https://openalex.org/W3037572520"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"is":[4,57,131],"a":[5,13,76,88,127,179],"challenging":[6],"video":[7,151],"understanding":[8,15,65],"task":[9],"since":[10],"it":[11],"requires":[12],"deep":[14],"of":[16,41,61,66,103,146],"both":[17,97],"question":[18,49],"and":[19,29,45,71,100,111,123,158,161,184],"video.":[20],"Previous":[21],"studies":[22],"mainly":[23],"focus":[24],"on":[25,178],"extracting":[26],"sophisticated":[27],"visual":[28,122,139],"language":[30],"embeddings,":[31],"fusing":[32],"them":[33],"by":[34,115,166],"delicate":[35],"hand-crafted":[36],"networks.":[37],"However,":[38],"the":[39,48,54,67,68,98,104,121,135,143,155,163,172,185,193],"relevance":[40],"different":[42,150],"frames,":[43,152],"objects,":[44],"modalities":[46],"to":[47,79,95,119,133,170],"are":[50,113],"varied":[51],"along":[52],"with":[53],"time,":[55],"which":[56],"ignored":[58],"in":[59,106,149],"most":[60],"existing":[62],"methods.":[63,195],"Lacking":[64],"dynamic":[69,101,144],"relationships":[70],"interactions":[72],"among":[73],"objects":[74,105,148],"brings":[75],"great":[77],"challenge":[78],"VideoQA":[80,182],"task.":[81],"To":[82,141],"address":[83],"this":[84],"problem,":[85],"we":[86,153],"propose":[87],"novel":[89],"Relation-aware":[90],"Hierarchical":[91],"Attention":[92],"(RHA)":[93],"framework":[94],"learn":[96],"static":[99,136],"relations":[102],"videos.":[107],"In":[108],"particular,":[109],"videos":[110],"questions":[112],"embedded":[114],"pre-trained":[116],"models":[117],"firstly":[118],"obtain":[120],"textual":[124],"features.":[125],"Then":[126],"graph-based":[128],"relation":[129],"encoder":[130],"utilized":[132],"extract":[134],"relationship":[137],"between":[138],"objects.":[140],"capture":[142],"changes":[145],"multimodal":[147,164],"consider":[154],"temporal,":[156],"spatial,":[157],"semantic":[159],"relations,":[160],"fuse":[162],"features":[165],"hierarchical":[167],"attention":[168],"mechanism":[169],"predict":[171],"answer.":[173],"We":[174],"conduct":[175],"extensive":[176],"experiments":[177],"large":[180],"scale":[181],"dataset,":[183],"experimental":[186],"results":[187],"demonstrate":[188],"that":[189],"our":[190],"RHA":[191],"outperforms":[192],"state-of-the-art":[194]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2021-05-24T00:00:00"}