{"id":"https://openalex.org/W4285600797","doi":"https://doi.org/10.24963/ijcai.2022/178","title":"Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering","display_name":"Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285600797","doi":"https://doi.org/10.24963/ijcai.2022/178"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/178","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/178","pdf_url":"https://www.ijcai.org/proceedings/2022/0178.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0178.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102012008","display_name":"Min Peng","orcid":"https://orcid.org/0000-0001-7445-5567"},"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"]},{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Peng","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210123021"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700778","display_name":"Chongyang Wang","orcid":"https://orcid.org/0000-0002-9819-088X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chongyang Wang","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722724","display_name":"Yuan Gao","orcid":"https://orcid.org/0000-0002-9336-0640"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Yuan Gao","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328458","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0003-1940-0074"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085205118","display_name":"Xiangdong Zhou","orcid":"https://orcid.org/0000-0002-5866-8682"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang-Dong Zhou","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210123021"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085205118"],"corresponding_institution_ids":["https://openalex.org/I4210123021"],"apc_list":null,"apc_paid":null,"fwci":1.4913,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88138842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1276","last_page":"1282"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9919000267982483,"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":0.8353667259216309},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7333828806877136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5606562495231628},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5382779240608215},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.483505517244339},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.44706231355667114},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.4451688826084137},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4325310289859772},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.21832463145256042},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16205370426177979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353667259216309},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7333828806877136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5606562495231628},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5382779240608215},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.483505517244339},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.44706231355667114},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4451688826084137},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4325310289859772},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.21832463145256042},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16205370426177979},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/178","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/178","pdf_url":"https://www.ijcai.org/proceedings/2022/0178.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10150093","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10150093/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.  (pp. pp. 1276-1282).  IJCAI: International Joint Conferences on Artificial Intelligence Organization (2022)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/178","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/178","pdf_url":"https://www.ijcai.org/proceedings/2022/0178.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G378428083","display_name":null,"funder_award_id":"62106247","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285600797.pdf","grobid_xml":"https://content.openalex.org/works/W4285600797.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2163046677","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2890598214","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2962934715","https://openalex.org/W2962949233","https://openalex.org/W2963563276","https://openalex.org/W2963954913","https://openalex.org/W2964057271","https://openalex.org/W2969127500","https://openalex.org/W2979826702","https://openalex.org/W2997344006","https://openalex.org/W2998166190","https://openalex.org/W3034512672","https://openalex.org/W3034730770","https://openalex.org/W3034772996","https://openalex.org/W3035419698","https://openalex.org/W3158039165","https://openalex.org/W3165924482","https://openalex.org/W3167092180","https://openalex.org/W3203995540","https://openalex.org/W4287112932","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W4381058564","https://openalex.org/W2964413124","https://openalex.org/W2986843960"],"abstract_inverted_index":{"Video":[0],"question":[1,96,126],"answering":[2,124],"(VideoQA)":[3],"is":[4,31],"challenging":[5],"given":[6],"its":[7],"multimodal":[8],"combination":[9],"of":[10,40,88,156,159],"visual":[11,23,103,114,133],"understanding":[12],"and":[13,75,94,152],"natural":[14],"language":[15],"processing.":[16],"While":[17],"most":[18],"existing":[19],"approaches":[20],"ignore":[21],"the":[22,36,86,95,100,113,132,154],"appearance-motion":[24,89],"information":[25,90,134],"at":[26,91,116,135],"different":[27,125],"temporal":[28],"scales,":[29],"it":[30],"unknown":[32],"how":[33],"to":[34,98,121],"incorporate":[35],"multilevel":[37,101],"processing":[38],"capacity":[39],"a":[41,55,81,107],"deep":[42],"learning":[43],"model":[44],"with":[45,61,106,123],"such":[46],"multiscale":[47,62,82],"information.":[48],"Targeting":[49],"these":[50],"issues,":[51],"this":[52],"paper":[53],"proposes":[54],"novel":[56],"Multilevel":[57],"Hierarchical":[58],"Network":[59],"(MHN)":[60],"sampling":[63],"for":[64],"VideoQA.":[65],"MHN":[66],"comprises":[67],"two":[68],"modules,":[69],"namely":[70],"Recurrent":[71],"Multimodal":[72],"Interaction":[73],"(RMI)":[74],"Parallel":[76],"Visual":[77],"Reasoning":[78],"(PVR).":[79],"With":[80],"sampling,":[83],"RMI":[84],"iterates":[85],"interaction":[87],"each":[92,117,157],"scale":[93],"embeddings":[97],"build":[99],"question-guided":[102],"representations.":[104],"Thereon,":[105],"shared":[108],"transformer":[109],"encoder,":[110],"PVR":[111],"infers":[112],"cues":[115],"level":[118],"in":[119],"parallel":[120],"fit":[122],"types":[127],"that":[128],"may":[129],"rely":[130],"on":[131,141],"relevant":[136],"levels.":[137],"Through":[138],"extensive":[139],"experiments":[140],"three":[142],"VideoQA":[143],"datasets,":[144],"we":[145],"demonstrate":[146],"improved":[147],"performances":[148],"than":[149],"previous":[150],"state-of-the-arts":[151],"justify":[153],"effectiveness":[155],"part":[158],"our":[160],"method.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}