{"id":"https://openalex.org/W7138469371","doi":"https://doi.org/10.1609/aaai.v40i1.36963","title":"ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid Reasoning","display_name":"ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid Reasoning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138469371","doi":"https://doi.org/10.1609/aaai.v40i1.36963"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i1.36963","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36963","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/36963/40925","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/36963/40925","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129730535","display_name":"Zongsheng Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zongsheng Cao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory\nTsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory\nTsinghua University","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129648375","display_name":"Anran Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anran Liu","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129646620","display_name":"Yangfan He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangfan He","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652431","display_name":"Jing Li","orcid":null},"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":"Jing Li","raw_affiliation_strings":["School of Economics and Management, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678275","display_name":"Bo Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103057256","display_name":"Zigan Wang","orcid":"https://orcid.org/0000-0001-5508-4836"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"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":"Zigan Wang","raw_affiliation_strings":["School of Economics and Management, Tsinghua University,\nShenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Tsinghua University,\nShenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76353276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"48","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9854999780654907,"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":0.9854999780654907,"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/T10028","display_name":"Topic Modeling","score":0.002899999963119626,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.002099999925121665,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.5313000082969666},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4794999957084656},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4359999895095825},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.41920000314712524},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36719998717308044},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.34540000557899475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8546000123023987},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228000283241272},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i1.36963","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36963","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/36963/40925","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/36963","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/36963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i1.36963","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36963","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/36963/40925","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5543264746665955}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138469371.pdf","grobid_xml":"https://content.openalex.org/works/W7138469371.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1,188],"(RAG)":[2],"has":[3],"greatly":[4],"improved":[5],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"by":[10,190],"adding":[11],"external":[12],"knowledge.":[13],"However,":[14],"current":[15,229],"RAG-based":[16,31,230],"methods":[17,32],"face":[18],"difficulties":[19],"with":[20,69,168],"long-context":[21,34,93],"video":[22,35,73,94,107,212],"understanding":[23,36,95],"due":[24],"to":[25,38,64,77,91,149,203],"two":[26],"main":[27],"challenges.":[28],"First,":[29],"Current":[30],"for":[33,121,163,184],"struggle":[37],"effectively":[39],"integrate":[40,204],"multimodal":[41],"and":[42,49,75,101,118,136,165,210],"long-range":[43,125],"temporal":[44,116,146,166],"information,":[45],"resulting":[46],"in":[47],"fragmented":[48],"context-insensitive":[50],"knowledge":[51,99,147],"representations.":[52],"Furthermore,":[53],"their":[54],"retrieval":[55,139,155,161,182],"mechanisms":[56],"often":[57],"rely":[58],"on":[59,221],"static":[60],"textual":[61,98],"matching,":[62],"failing":[63],"dynamically":[65,142],"align":[66],"user":[67],"queries":[68],"the":[70,173,180],"most":[71],"relevant":[72],"segments":[74],"leading":[76],"suboptimal":[78],"downstream":[79],"performance.":[80],"To":[81,153],"overcome":[82],"these":[83],"issues,":[84],"we":[85,105,157],"introduce":[86],"ViG-RAG,":[87],"a":[88,132,137,144,159,200],"new":[89],"framework":[90],"enhance":[92],"through":[96],"structured":[97,110],"grounding":[100,134],"multi-modal":[102],"retrieval.":[103],"Specifically,":[104],"segment":[106],"transcripts":[108],"into":[109],"units,":[111],"extract":[112],"key":[113],"entities,":[114],"form":[115],"connections,":[117],"assign":[119],"confidence":[120],"evidence,":[122],"enabling":[123],"coherent":[124],"reasoning.":[126],"In":[127,175],"this":[128,176],"way,":[129,177],"it":[130,178,226],"utilizes":[131],"knowledge-aware":[133],"mechanism":[135],"context-aware":[138],"process":[140],"that":[141,225],"builds":[143],"probabilistic":[145],"graph":[148],"organize":[150],"multi-video":[151],"content.":[152],"improve":[154],"accuracy,":[156],"propose":[158],"hybrid":[160],"strategy":[162],"semantic":[164,205],"features,":[167],"an":[169,215],"adaptive":[170],"distribution":[171,183],"modeling":[172],"relevance.":[174],"achieves":[179],"optimal":[181],"each":[185],"query,":[186],"enhancing":[187],"efficiency":[189],"reducing":[191],"unnecessary":[192],"computations.":[193],"On":[194],"top":[195],"of":[196],"this,":[197],"ViG-RAG":[198,220],"uses":[199],"vision-language":[201],"model":[202],"anchors,":[206],"expanded":[207],"contextual":[208],"fields,":[209],"selected":[211],"frames,":[213],"generating":[214],"accurate":[216],"response.":[217],"We":[218],"evaluate":[219],"several":[222],"benchmarks,":[223],"demonstrating":[224],"significantly":[227],"surpasses":[228],"methods.":[231]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}