{"id":"https://openalex.org/W4391407221","doi":"https://doi.org/10.1109/tip.2024.3358726","title":"Event Graph Guided Compositional Spatial\u2013Temporal Reasoning for Video Question Answering","display_name":"Event Graph Guided Compositional Spatial\u2013Temporal Reasoning for Video Question Answering","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391407221","doi":"https://doi.org/10.1109/tip.2024.3358726","pmid":"https://pubmed.ncbi.nlm.nih.gov/38294915"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3358726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3358726","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102798840","display_name":"Ziyi Bai","orcid":"https://orcid.org/0009-0004-5917-5400"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Bai","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-5917-5400","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614962","display_name":"Ruiping Wang","orcid":"https://orcid.org/0000-0003-1830-2595"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiping Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1830-2595","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133932","display_name":"Difei Gao","orcid":"https://orcid.org/0000-0001-8494-3492"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Difei Gao","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8494-3492","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083420537","display_name":"Xilin Chen","orcid":"https://orcid.org/0000-0003-3024-4404"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3024-4404","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6223,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.830121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"33","issue":null,"first_page":"1109","last_page":"1121"},"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":0.9979000091552734,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.6520140171051025},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.535894513130188},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5169836282730103},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5092242956161499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48852241039276123},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3503679931163788},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3247145414352417},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2856137752532959}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6520140171051025},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.535894513130188},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5169836282730103},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5092242956161499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48852241039276123},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3503679931163788},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3247145414352417},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2856137752532959},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3358726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3358726","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:38294915","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38294915","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G370319998","display_name":null,"funder_award_id":"2021ZD0111901","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3848188706","display_name":null,"funder_award_id":"U19B2036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4523261873","display_name":null,"funder_award_id":"U21B2025","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2013894622","https://openalex.org/W2090048052","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2337252826","https://openalex.org/W2549139847","https://openalex.org/W2560730294","https://openalex.org/W2565639579","https://openalex.org/W2579549467","https://openalex.org/W2886970679","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2962677524","https://openalex.org/W2962949233","https://openalex.org/W2963518342","https://openalex.org/W2963524571","https://openalex.org/W2963644680","https://openalex.org/W2981851019","https://openalex.org/W2981985547","https://openalex.org/W2983918066","https://openalex.org/W2997344006","https://openalex.org/W2998166190","https://openalex.org/W3003991937","https://openalex.org/W3009148386","https://openalex.org/W3034679267","https://openalex.org/W3034730770","https://openalex.org/W3035017890","https://openalex.org/W3035265375","https://openalex.org/W3035702572","https://openalex.org/W3093804672","https://openalex.org/W3120889656","https://openalex.org/W3122622502","https://openalex.org/W3167092180","https://openalex.org/W3168640669","https://openalex.org/W3175625489","https://openalex.org/W3181758331","https://openalex.org/W3186621246","https://openalex.org/W3187433838","https://openalex.org/W3197457832","https://openalex.org/W3203995540","https://openalex.org/W4200631219","https://openalex.org/W4283801188","https://openalex.org/W4295036294","https://openalex.org/W4312245888","https://openalex.org/W4312317310","https://openalex.org/W4312864639","https://openalex.org/W4313071966","https://openalex.org/W4385572645","https://openalex.org/W4386066129","https://openalex.org/W4386071577","https://openalex.org/W4386075753","https://openalex.org/W4386076413","https://openalex.org/W4386076518","https://openalex.org/W6620707391","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6774097426","https://openalex.org/W6789619165","https://openalex.org/W6797109355","https://openalex.org/W6803023527","https://openalex.org/W6810334672","https://openalex.org/W6846765560","https://openalex.org/W6847695204"],"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],"is":[4,232],"challenging":[5,203],"since":[6],"it":[7],"requires":[8],"the":[9,33,41,46,60,107,118,124,129,133,138,141,159,168,187,191,196,201,210,215],"model":[10,42],"to":[11,21,58,73,112,166,174],"extract":[12],"and":[13,82,84,148,195,205],"combine":[14,167],"multi-level":[15,192],"visual":[16,74,110],"concepts":[17,48,75],"from":[18,24,106,128],"local":[19],"objects":[20],"global":[22],"actions":[23],"complex":[25],"events":[26],"for":[27],"compositional":[28,114],"reasoning.":[29],"Existing":[30],"works":[31],"represent":[32,59],"video":[34,61],"with":[35,62,152,226],"fixed-duration":[36],"clip":[37],"features":[38],"that":[39,209],"make":[40],"struggle":[43],"in":[44,49,66,140],"capturing":[45],"crucial":[47],"multiple":[50],"granularities.":[51],"To":[52,121],"overcome":[53],"this":[54],"shortcoming,":[55],"we":[56,136,162],"propose":[57,92],"an":[63],"Event":[64],"Graph":[65],"a":[67,93,220],"hierarchical":[68,188],"structure":[69],"whose":[70],"nodes":[71,105,139,172],"correspond":[72],"of":[76,143],"different":[77],"levels":[78],"(object,":[79],"relation,":[80],"scene":[81],"action)":[83],"edges":[85],"indicate":[86],"their":[87,144,175],"spatial-temporal":[88,125,169],"relationships.":[89],"We":[90],"further":[91],"H":[94],"ierarchical":[95],"S":[96],"patial-":[97],"T":[98,100],"emporal":[99],"ransformer":[101],"(HSTT)":[102],"which":[103],"takes":[104],"graph":[108,130,155,194],"as":[109],"input":[111],"realize":[113],"reasoning":[115],"guided":[116],"by":[117,182,186,219],"event":[119,193],"graph.":[120],"fully":[122],"exploit":[123],"context":[126,170],"delivered":[127],"structure,":[131],"on":[132,200],"one":[134],"hand,":[135,161],"encode":[137],"order":[142],"semantic":[145],"hierarchy":[146],"(depth)":[147],"occurrence":[149],"time":[150],"(breadth)":[151],"our":[153],"improved":[154],"search":[156],"algorithm;":[157],"On":[158],"other":[160],"introduce":[163],"edge-guided":[164],"attention":[165],"among":[171],"according":[173],"edge":[176],"connections.":[177],"HSTT":[178],"then":[179],"performs":[180],"QA":[181],"cross-modal":[183],"interactions":[184],"guaranteed":[185],"correspondence":[189],"between":[190],"cross-level":[197],"question.":[198],"Experiments":[199],"recent":[202],"AGQA":[204],"STAR":[206],"datasets":[207],"show":[208],"proposed":[211],"method":[212],"clearly":[213],"outperforms":[214],"existing":[216],"VideoQA":[217],"models":[218],"large":[221],"margin,":[222],"including":[223],"those":[224],"pre-trained":[225],"large-scale":[227],"external":[228],"data.":[229],"Our":[230],"code":[231],"available":[233],"at":[234],"https://github.com/ByZ0e/HSTT.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}