{"id":"https://openalex.org/W3175625489","doi":"https://doi.org/10.24963/ijcai.2021/88","title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","display_name":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3175625489","doi":"https://doi.org/10.24963/ijcai.2021/88","mag":"3175625489"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/88","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/88","pdf_url":"https://www.ijcai.org/proceedings/2021/0088.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0088.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008734340","display_name":"Long Hoang Dang","orcid":"https://orcid.org/0000-0002-2701-2365"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Long Hoang Dang","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, Australia","Deakin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"Deakin University","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079045166","display_name":"Thao Minh Le","orcid":"https://orcid.org/0000-0002-8089-9962"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thao Minh Le","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, Australia","Deakin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"Deakin University","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029157904","display_name":"Vuong Le","orcid":"https://orcid.org/0000-0003-1582-1269"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vuong Le","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, Australia","Deakin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"Deakin University","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085471517","display_name":"Truyen Tran","orcid":"https://orcid.org/0000-0001-6531-8907"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Truyen Tran","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, Australia","Deakin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"Deakin University","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"642"},"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":0.9984999895095825,"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":0.9884999990463257,"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":0.8357621431350708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5699000954627991},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4361379146575928},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4293256402015686},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4184434711933136},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41628536581993103},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4136057496070862},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3289564251899719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357621431350708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5699000954627991},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4361379146575928},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4293256402015686},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4184434711933136},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41628536581993103},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4136057496070862},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3289564251899719},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.24963/ijcai.2021/88","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/88","pdf_url":"https://www.ijcai.org/proceedings/2021/0088.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.13432","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.13432","pdf_url":"https://arxiv.org/pdf/2106.13432","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"},{"id":"mag:3175625489","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2106.13432.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:dro.deakin.edu.au:DU:30158850","is_oa":false,"landing_page_url":"http://doi.org/10.24963/ijcai.2021/88","pdf_url":null,"source":{"id":"https://openalex.org/S4306402457","display_name":"Deakin Research Online (Deakin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:figshare.com:article/20635329","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Hierarchical_Object-oriented_Spatio-Temporal_Reasoning_for_Video_Question_Answering/20635329","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},{"id":"doi:10.48550/arxiv.2106.13432","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.13432","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/88","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/88","pdf_url":"https://www.ijcai.org/proceedings/2021/0088.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3175625489.pdf","grobid_xml":"https://content.openalex.org/works/W3175625489.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2603203130","https://openalex.org/W2606982687","https://openalex.org/W2611596598","https://openalex.org/W2737435850","https://openalex.org/W2765716052","https://openalex.org/W2798786641","https://openalex.org/W2806331055","https://openalex.org/W2808124938","https://openalex.org/W2808675313","https://openalex.org/W2890598214","https://openalex.org/W2897857500","https://openalex.org/W2952620298","https://openalex.org/W2954199749","https://openalex.org/W2962876901","https://openalex.org/W2962910007","https://openalex.org/W2962949233","https://openalex.org/W2963155035","https://openalex.org/W2963165299","https://openalex.org/W2963305465","https://openalex.org/W2964121744","https://openalex.org/W2964146787","https://openalex.org/W2965527197","https://openalex.org/W2986407524","https://openalex.org/W2995993311","https://openalex.org/W2997344006","https://openalex.org/W3010593057","https://openalex.org/W3034730770","https://openalex.org/W3035392611"],"related_works":["https://openalex.org/W3189890868","https://openalex.org/W3198966763","https://openalex.org/W2981774933","https://openalex.org/W2267167212","https://openalex.org/W3034513622","https://openalex.org/W3118493476","https://openalex.org/W2966369713","https://openalex.org/W2808675313","https://openalex.org/W3129640956","https://openalex.org/W3034636873","https://openalex.org/W3090193843","https://openalex.org/W3121327184","https://openalex.org/W2986755220","https://openalex.org/W3124461501","https://openalex.org/W3136464356","https://openalex.org/W2998631105","https://openalex.org/W2958301808","https://openalex.org/W1533712238","https://openalex.org/W1996927234","https://openalex.org/W3170410460"],"abstract_inverted_index":{"Video":[0,183,210],"Question":[1],"Answering":[2],"(Video":[3],"QA)":[4],"is":[5,64,108,178,202],"a":[6,67,104,111,140,163,203],"powerful":[7],"testbed":[8],"to":[9,18,41,95,209],"develop":[10],"new":[11,188],"AI":[12],"capabilities.":[13],"This":[14,106,128],"task":[15],"necessitates":[16],"learning":[17],"reason":[19],"about":[20,92],"objects,":[21,46],"relations,":[22],"and":[23,27,49,87,98,117,166,186,206],"events":[24],"across":[25],"visual":[26,38],"linguistic":[28],"domains":[29],"in":[30,61,136,162,190],"space-time.":[31],"High-level":[32],"reasoning":[33,59,201],"demands":[34],"lifting":[35],"from":[36],"associative":[37],"pattern":[39],"recognition":[40],"symbol":[42],"like":[43],"manipulation":[44],"over":[45],"their":[47,88,118],"behavior":[48,197],"interactions.":[50],"Toward":[51],"reaching":[52],"this":[53,146],"goal":[54],"we":[55],"propose":[56],"an":[57],"object-oriented":[58,151,200],"approach":[60,208],"that":[62,199],"video":[63,78,158],"abstracted":[65,161],"as":[66],"dynamic":[68,149],"stream":[69],"of":[70,76,103,113,139],"interacting":[71],"objects.":[72],"At":[73],"each":[74,85],"stage":[75],"the":[77,96,100,132,137,148,157,169,173,195],"event":[79],"flow,":[80],"these":[81,191],"objects":[82],"interact":[83],"with":[84,93],"other,":[86],"interactions":[89],"are":[90,153],"reasoned":[91],"respect":[94],"query":[97],"under":[99],"overall":[101],"context":[102],"video.":[105],"mechanism":[107],"materialized":[109],"into":[110,194],"family":[112],"general-purpose":[114],"neural":[115,129],"units":[116],"multi-level":[119],"architecture":[120],"called":[121],"Hierarchical":[122],"Object-oriented":[123],"Spatio-Temporal":[124],"Reasoning":[125],"(HOSTR)":[126],"networks.":[127],"model":[130],"maintains":[131],"objects'":[133],"consistent":[134],"lifelines":[135],"form":[138],"hierarchically":[141,160],"nested":[142],"spatio-temporal":[143],"graph.":[144],"Within":[145],"graph,":[147],"interactive":[150],"representations":[152],"built":[154],"up":[155],"along":[156],"sequence,":[159],"bottom-up":[164],"manner,":[165],"converge":[167],"toward":[168],"key":[170],"information":[171],"for":[172],"correct":[174],"answer.":[175],"The":[176],"method":[177],"evaluated":[179],"on":[180],"multiple":[181],"major":[182],"QA":[184],"datasets":[185],"establishes":[187],"state-of-the-arts":[189],"tasks.":[192],"Analysis":[193],"model's":[196],"indicates":[198],"reliable,":[204],"interpretable":[205],"efficient":[207],"QA.":[211]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
