{"id":"https://openalex.org/W4304084136","doi":"https://doi.org/10.1145/3503161.3548061","title":"Dynamic Spatio-Temporal Modular Network for Video Question Answering","display_name":"Dynamic Spatio-Temporal Modular Network for Video Question Answering","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304084136","doi":"https://doi.org/10.1145/3503161.3548061"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548061","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548061","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045286456","display_name":"Zi Qian","orcid":"https://orcid.org/0000-0002-8011-6147"},"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":"Zi Qian","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"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":"Xin Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028258340","display_name":"Xuguang Duan","orcid":"https://orcid.org/0000-0001-9108-9618"},"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":"Xuguang Duan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420416","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-0943-2286"},"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":"Hong Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"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":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5899,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.76680628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4466","last_page":"4477"},"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":0.9965000152587891,"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":0.851314902305603},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.8368003368377686},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7644730806350708},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.643683910369873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5845525860786438},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5555334091186523},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5407896041870117},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5350692272186279},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4865366518497467},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4163370430469513},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3443015515804291},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11269214749336243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.851314902305603},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.8368003368377686},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7644730806350708},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.643683910369873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5845525860786438},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5555334091186523},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5407896041870117},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5350692272186279},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4865366518497467},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4163370430469513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3443015515804291},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11269214749336243},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548061","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3548061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548061","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G119957897","display_name":null,"funder_award_id":"62102222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1527691513","display_name":null,"funder_award_id":"62250008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3720940119","display_name":null,"funder_award_id":"2020AAA0106300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6655011991","display_name":null,"funder_award_id":"No. 2020AAA0106300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7084459132","display_name":null,"funder_award_id":"No. 62250008, No. 62102222","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304084136.pdf","grobid_xml":"https://content.openalex.org/works/W4304084136.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1933349210","https://openalex.org/W2082435639","https://openalex.org/W2121863487","https://openalex.org/W2123402141","https://openalex.org/W2561715562","https://openalex.org/W2606982687","https://openalex.org/W2751525844","https://openalex.org/W2765716052","https://openalex.org/W2793546384","https://openalex.org/W2808181286","https://openalex.org/W2883104598","https://openalex.org/W2904452845","https://openalex.org/W2949789546","https://openalex.org/W2954199749","https://openalex.org/W2962716332","https://openalex.org/W2962858109","https://openalex.org/W2962949233","https://openalex.org/W2963224792","https://openalex.org/W2963781647","https://openalex.org/W2964118342","https://openalex.org/W2969127500","https://openalex.org/W2972113750","https://openalex.org/W2981721414","https://openalex.org/W2997344006","https://openalex.org/W2998166190","https://openalex.org/W3034679267","https://openalex.org/W3034730770","https://openalex.org/W3099849198","https://openalex.org/W3118500473","https://openalex.org/W3122622502","https://openalex.org/W3159630763","https://openalex.org/W3167092180","https://openalex.org/W3168640669","https://openalex.org/W3187433838","https://openalex.org/W3203995540","https://openalex.org/W3206675006","https://openalex.org/W3207847779","https://openalex.org/W4221154653","https://openalex.org/W4239181501","https://openalex.org/W6754478056","https://openalex.org/W6803023527"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"aims":[4],"to":[5,27,42,51,79,151,179,204],"understand":[6],"given":[7,96],"videos":[8,111],"and":[9,110,138,199,211],"questions":[10,56,109],"comprehensively":[11],"by":[12],"generating":[13],"correct":[14],"answers.":[15],"However,":[16],"existing":[17,48],"methods":[18,49,190],"usually":[19],"rely":[20],"on":[21,104,175],"end-to-end":[22],"black-box":[23],"deep":[24],"neural":[25,157],"networks":[26],"infer":[28],"the":[29,40,45,81,91,164,168,176,206,212,215],"answers,":[30],"which":[31,73],"significantly":[32,186],"differs":[33],"from":[34],"human":[35,86],"logic":[36,136],"reasoning,":[37],"thus":[38],"lacking":[39],"ability":[41],"explain.":[43],"Besides,":[44],"performances":[46],"of":[47,85,93,101,208,214],"tend":[50],"drop":[52],"when":[53],"answering":[54,94],"compositional":[55,82],"involving":[57],"realistic":[58],"scenarios.":[59],"To":[60],"tackle":[61],"these":[62],"challenges,":[63],"we":[64,89,142,195],"propose":[65],"a":[66,75,95,99,125,153],"Dynamic":[67],"Spatio-Temporal":[68],"Modular":[69],"Network":[70],"(DSTN)":[71],"model,":[72],"utilizes":[74],"spatio-temporal":[76,155],"modular":[77,156],"network":[78,158],"simulate":[80],"reasoning":[83,161,202],"procedure":[84],"beings.":[87],"Concretely,":[88],"divide":[90],"task":[92],"question":[97],"into":[98],"set":[100],"sub-tasks":[102,150],"focusing":[103],"certain":[105],"key":[106],"concepts":[107],"in":[108,191],"such":[112],"as":[113],"objects,":[114],"actions,":[115],"temporal":[116,133],"orders,":[117],"etc.":[118],"Each":[119],"sub-task":[120],"can":[121,185],"be":[122],"solved":[123],"with":[124,148],"separately":[126],"designed":[127],"module,":[128,132,135,137],"e.g.,":[129],"spatial":[130],"attention":[131,134],"answer":[139,166],"module.":[140],"Then":[141],"dynamically":[143],"assemble":[144],"different":[145,149,209],"modules":[146,210],"assigned":[147],"generate":[152],"tree-structured":[154],"for":[159,167],"human-like":[160],"before":[162],"producing":[163],"final":[165],"question.":[169],"We":[170],"carry":[171],"out":[172],"extensive":[173],"experiments":[174],"AGQA":[177],"dataset":[178],"demonstrate":[180],"our":[181],"proposed":[182,216],"DSTN":[183,217],"model":[184],"outperform":[187],"several":[188],"baseline":[189],"various":[192],"settings.":[193],"Moreover,":[194],"evaluate":[196],"intermediate":[197],"results":[198],"visualize":[200],"each":[201],"step":[203],"verify":[205],"rationality":[207],"explainability":[213],"model.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}