{"id":"https://openalex.org/W4293518014","doi":"https://doi.org/10.1109/icme52920.2022.9859784","title":"FHGN: Frame-Level Heterogeneous Graph Networks for Video Question Answering","display_name":"FHGN: Frame-Level Heterogeneous Graph Networks for Video Question Answering","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518014","doi":"https://doi.org/10.1109/icme52920.2022.9859784"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859784","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5102989916","display_name":"Jinsheng Qi","orcid":"https://orcid.org/0009-0008-5058-6042"},"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":"Jinsheng Qi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103101177","display_name":"Fangtao Li","orcid":"https://orcid.org/0000-0002-8640-3235"},"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":"Fangtao Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101588982","display_name":"Ting Bai","orcid":"https://orcid.org/0000-0001-8466-4223"},"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,China","Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia, China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086286396","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,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067090170","display_name":"Wei Song","orcid":"https://orcid.org/0000-0002-5909-9661"},"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":"Wei Song","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101908081","display_name":"Yibo Hu","orcid":"https://orcid.org/0009-0006-7762-6986"},"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":"Yibo Hu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043114890","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0001-5787-9536"},"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,China","Beijing University of Posts and Telecommunications, China","Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.177,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50149042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"06"},"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":0.9976000189781189,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9954000115394592,"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/modalities","display_name":"Modalities","score":0.7773442268371582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7497298121452332},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5768604278564453},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5742378234863281},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5662253499031067},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5320362448692322},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.49932360649108887},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.49537789821624756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49520745873451233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38221463561058044},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2825767397880554}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7773442268371582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497298121452332},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5768604278564453},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5742378234863281},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5662253499031067},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5320362448692322},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.49932360649108887},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49537789821624756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49520745873451233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38221463561058044},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2825767397880554},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/icme52920.2022.9859784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859784","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3915844376","display_name":"\u878d\u5408\u89c6\u9891\u6570\u636e\u7684\u793e\u4ea4\u7f51\u7edc\u5e7f\u5ea6\u5b66\u4e60\u7b97\u6cd5\u7814\u7a76","funder_award_id":"61972047","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2606982687","https://openalex.org/W2806331055","https://openalex.org/W2896457183","https://openalex.org/W2900619470","https://openalex.org/W2904452845","https://openalex.org/W2963541336","https://openalex.org/W2964015378","https://openalex.org/W2966683369","https://openalex.org/W2985076077","https://openalex.org/W2998166190","https://openalex.org/W3004413500","https://openalex.org/W3034636873","https://openalex.org/W3092226176","https://openalex.org/W3160451259","https://openalex.org/W3163971663","https://openalex.org/W3167092180","https://openalex.org/W3173367591","https://openalex.org/W3189890868","https://openalex.org/W3197240429","https://openalex.org/W4287125738","https://openalex.org/W6726873649","https://openalex.org/W6751936687","https://openalex.org/W6755207826","https://openalex.org/W6756549752","https://openalex.org/W6797109355"],"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/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA),":[3],"aims":[4],"to":[5,60,71,90,104],"answer":[6],"the":[7,42,45,52,61,73,106,109,128,136],"given":[8],"question":[9,110],"based":[10],"on":[11,122],"video":[12],"grounding,":[13],"reasoning,":[14],"and":[15,25,50,58,94,111,116,127],"multimodal":[16],"interacting.":[17],"Most":[18],"existing":[19],"studies":[20],"usually":[21],"extract":[22],"video-level":[23],"visual":[24],"linguistic":[26],"embeddings":[27],"separately,":[28],"then":[29],"perform":[30,91],"spatial-temporal":[31],"or":[32],"graph-based":[33],"reasoning":[34],"in":[35,79],"a":[36,85,98,123],"single":[37],"modality.":[38],"These":[39],"methods":[40],"lack":[41],"understanding":[43],"of":[44,54],"interactions":[46],"among":[47,76],"different":[48,55,77,112],"modalities":[49,59,78],"ignore":[51],"rele-vance":[53],"frames,":[56],"objects,":[57],"question.":[62],"This":[63],"paper":[64],"proposes":[65],"Frame-level":[66],"Heterogeneous":[67],"Graph":[68],"Networks":[69],"(FHGN),":[70],"learn":[72],"semantic":[74],"correlations":[75],"each":[80],"frame.":[81],"Specifically,":[82],"we":[83],"construct":[84],"uniform":[86],"frame-level":[87],"heterogeneous":[88],"graph":[89],"both":[92],"inter-":[93],"intra-modality":[95],"reasoning.":[96],"Then":[97],"two-stage":[99],"attention":[100],"module":[101],"is":[102],"applied":[103],"measure":[105],"relevance":[107],"between":[108],"periods,":[113],"space":[114],"regions,":[115],"modalities.":[117],"We":[118],"conduct":[119],"extensive":[120],"experiments":[121],"large-scale":[124],"VideoQA":[125],"dataset,":[126],"experimental":[129],"results":[130],"show":[131],"that":[132],"our":[133],"FHGN":[134],"achieves":[135],"state-of-the-art":[137],"performance.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}