{"id":"https://openalex.org/W4400228558","doi":"https://doi.org/10.1109/tip.2024.3411448","title":"Dynamic Spatio-Temporal Graph Reasoning for VideoQA With Self-Supervised Event Recognition","display_name":"Dynamic Spatio-Temporal Graph Reasoning for VideoQA With Self-Supervised Event Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400228558","doi":"https://doi.org/10.1109/tip.2024.3411448","pmid":"https://pubmed.ncbi.nlm.nih.gov/38954578"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3411448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3411448","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/A5058652390","display_name":"Jie Nie","orcid":"https://orcid.org/0000-0003-4952-7666"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Nie","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-4952-7666","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"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":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0351-2939","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024495682","display_name":"Runze Hou","orcid":"https://orcid.org/0000-0002-9697-7996"},"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":"Runze Hou","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9697-7996","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002254187","display_name":"Guohao Li","orcid":"https://orcid.org/0000-0001-7796-5378"},"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":"Guohao Li","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, 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":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0943-2286","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, 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":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2236-9290","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7184,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9437908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"33","issue":null,"first_page":"4145","last_page":"4158"},"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":0.9962000250816345,"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":0.9872000217437744,"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":0.8176615238189697},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6801713705062866},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6480988264083862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6040419936180115},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5977030396461487},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5757969617843628},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.484336256980896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4660687744617462},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43754351139068604},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.41241714358329773},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.23830914497375488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176615238189697},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6801713705062866},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6480988264083862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6040419936180115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5977030396461487},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5757969617843628},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.484336256980896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4660687744617462},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43754351139068604},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.41241714358329773},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.23830914497375488},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3411448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3411448","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:38954578","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38954578","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/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/G1622659961","display_name":null,"funder_award_id":"2023YFF1205001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4707258129","display_name":null,"funder_award_id":"U23A20320","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8567821897","display_name":null,"funder_award_id":"62222209","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":73,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1836465849","https://openalex.org/W1923404803","https://openalex.org/W1947481528","https://openalex.org/W1983364832","https://openalex.org/W2105101328","https://openalex.org/W2108333036","https://openalex.org/W2126574503","https://openalex.org/W2194775991","https://openalex.org/W2308529009","https://openalex.org/W2425121537","https://openalex.org/W2549139847","https://openalex.org/W2561715562","https://openalex.org/W2565639579","https://openalex.org/W2737435850","https://openalex.org/W2760103357","https://openalex.org/W2765716052","https://openalex.org/W2793546384","https://openalex.org/W2806331055","https://openalex.org/W2888096830","https://openalex.org/W2896457183","https://openalex.org/W2907820376","https://openalex.org/W2951702519","https://openalex.org/W2954199749","https://openalex.org/W2962688385","https://openalex.org/W2962716332","https://openalex.org/W2962949233","https://openalex.org/W2963150697","https://openalex.org/W2963155035","https://openalex.org/W2963224792","https://openalex.org/W2963420272","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2964015378","https://openalex.org/W2964118342","https://openalex.org/W2964322347","https://openalex.org/W2981721414","https://openalex.org/W2981851019","https://openalex.org/W2995993311","https://openalex.org/W2997344006","https://openalex.org/W3000279895","https://openalex.org/W3023371261","https://openalex.org/W3034257141","https://openalex.org/W3034287395","https://openalex.org/W3034730770","https://openalex.org/W3035725276","https://openalex.org/W3095013945","https://openalex.org/W3099768435","https://openalex.org/W3099849198","https://openalex.org/W3159630763","https://openalex.org/W3173367591","https://openalex.org/W3174001836","https://openalex.org/W3181758331","https://openalex.org/W3187433838","https://openalex.org/W4297749157","https://openalex.org/W4320351091","https://openalex.org/W4386071468","https://openalex.org/W4386075753","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6682864246","https://openalex.org/W6748270630","https://openalex.org/W6752083267","https://openalex.org/W6755207826","https://openalex.org/W6761069331","https://openalex.org/W6765591853","https://openalex.org/W6766904570","https://openalex.org/W6768853884","https://openalex.org/W6803023527","https://openalex.org/W6850206515","https://openalex.org/W7015296915"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Video":[0],"question":[1,122],"answering":[2,123],"(VideoQA)":[3],"requires":[4],"the":[5,54,63,88,100,145,148,188],"ability":[6],"of":[7,91,191],"comprehensively":[8],"understanding":[9],"visual":[10,56],"contents":[11],"in":[12,84,105,144,168],"videos.":[13,146],"Existing":[14],"VideoQA":[15,45,174],"models":[16,46],"mainly":[17],"focus":[18],"on":[19,50],"scenarios":[20,32],"involving":[21,33],"a":[22,71,75,113,129],"single":[23],"event":[24,164],"with":[25,36,161],"simple":[26],"object":[27,39,82],"interactions":[28,40,83],"and":[29,65,96,139],"leave":[30],"event-centric":[31],"multiple":[34],"events":[35],"dynamically":[37,134],"complex":[38],"largely":[41],"unexplored.":[42],"These":[43],"conventional":[44],"are":[47],"usually":[48],"based":[49],"features":[51],"extracted":[52],"from":[53,155],"global":[55],"signals,":[57],"making":[58],"it":[59,86],"difficult":[60],"to":[61,79,98,157,171,186],"capture":[62],"object-level":[64],"event-level":[66,102,153],"semantics.":[67],"Although":[68],"there":[69],"exists":[70],"recent":[72],"work":[73],"utilizing":[74],"static":[76],"spatio-temporal":[77,131],"graph":[78,94,132],"explicitly":[80],"model":[81,119,127,151,195],"videos,":[85],"ignores":[87],"dynamic":[89],"impact":[90],"questions":[92,156],"for":[93,120],"construction":[95],"fails":[97],"exploit":[99],"implicit":[101],"semantic":[103],"clues":[104],"questions.":[106],"To":[107],"overcome":[108],"these":[109],"limitations,":[110],"we":[111],"propose":[112],"Self-supervised":[114],"Dynamic":[115],"Graph":[116],"Reasoning":[117],"(SDGraphR)":[118],"video":[121],"(VideoQA).":[124],"Our":[125],"SDGraphR":[126,150,194],"learns":[128],"question-guided":[130],"that":[133],"encodes":[135],"intra-frame":[136],"spatial":[137],"correlations":[138],"inter-frame":[140],"correspondences":[141],"between":[142],"objects":[143],"Furthermore,":[147],"proposed":[149,193],"discovers":[152],"cues":[154],"conduct":[158],"self-supervised":[159],"learning":[160],"an":[162],"auxiliary":[163],"recognition":[165],"task,":[166],"which":[167],"turn":[169],"helps":[170],"improve":[172],"its":[173],"performances":[175],"without":[176],"using":[177],"any":[178],"extra":[179],"annotations.":[180],"We":[181],"carry":[182],"out":[183],"extensive":[184],"experiments":[185],"validate":[187],"substantial":[189],"improvements":[190],"our":[192],"over":[196],"existing":[197],"baselines.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}