{"id":"https://openalex.org/W7166889669","doi":"https://doi.org/10.18653/v1/2026.acl-long.1656","title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","display_name":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166889669","doi":"https://doi.org/10.18653/v1/2026.acl-long.1656"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1656","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1656","pdf_url":"https://aclanthology.org/2026.acl-long.1656.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1656.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139823573","display_name":"Honghao Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Honghao Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139777897","display_name":"Miao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139804582","display_name":"Yiwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiwei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139827219","display_name":"Dailing Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dailing Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139734155","display_name":"Jun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139779746","display_name":"Yujun Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.88557273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35793","last_page":"35805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.14949999749660492,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.14949999749660492,"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/T11439","display_name":"Video Analysis and Summarization","score":0.09120000153779984,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06880000233650208,"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/perspective","display_name":"Perspective (graphical)","score":0.28360000252723694},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.26750001311302185},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2556000053882599},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2433999925851822},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2305999994277954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.541700005531311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37290000915527344},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2433999925851822},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2305999994277954},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.22869999706745148},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.22439999878406525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1656","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1656","pdf_url":"https://aclanthology.org/2026.acl-long.1656.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1656","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1656","pdf_url":"https://aclanthology.org/2026.acl-long.1656.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.40671974420547485,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1294669936","display_name":"CRII: RI: Synergistic Learning of Language Models and Knowledge Graphs for Trustworthy Question Answering","funder_award_id":"2451683","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320333031","display_name":"University of California Merced","ror":"https://ror.org/00d9ah105"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166889669.pdf","grobid_xml":"https://content.openalex.org/works/W7166889669.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scaling":[0],"multimodal":[1],"large":[2],"language":[3],"models":[4],"(MLLMs)":[5],"to":[6,60,93,159],"long":[7],"videos":[8,36],"is":[9,18,138],"constrained":[10],"by":[11,22],"limited":[12],"context":[13],"windows.While":[14],"retrievalaugmented":[15],"generation":[16],"(RAG)":[17],"a":[19,28,70,79,82,126],"promising":[20],"remedy":[21],"organizing":[23],"query-relevant":[24],"visual":[25],"evidence":[26,95],"into":[27,37],"compact":[29],"context,":[30],"most":[31],"existing":[32],"methods":[33],"(i)":[34],"flatten":[35],"independent":[38],"segments,":[39],"breaking":[40],"their":[41,113],"inherent":[42],"spatio-temporal":[43],"structure,":[44],"and":[45,72,88,163],"(ii)":[46],"depend":[47],"on":[48,112,145],"explicit":[49],"semantic":[50,157],"matching,":[51],"which":[52],"can":[53],"miss":[54],"cues":[55],"that":[56,108,136],"are":[57,165],"implicitly":[58],"relevant":[59],"the":[61,116,149],"query's":[62,117],"intent.To":[63,119],"overcome":[64],"these":[65],"limitations,":[66],"we":[67,123],"propose":[68],"VideoStir,":[69],"structured":[71],"intent-aware":[73,161],"long-video":[74,153],"RAG":[75,154],"framework.It":[76],"firstly":[77],"structures":[78],"video":[80],"as":[81],"spatiotemporal":[83],"graph":[84],"at":[85,167],"clip":[86],"level,":[87],"then":[89],"performs":[90],"multi-hop":[91],"retrieval":[92],"aggregate":[94],"across":[96],"distant":[97],"yet":[98],"contextually":[99],"related":[100],"events.Furthermore,":[101],"it":[102],"introduces":[103],"an":[104],"MLLM-backed":[105],"intentrelevance":[106],"scorer":[107],"retrieves":[109],"frames":[110],"based":[111],"alignment":[114],"with":[115,140],"reasoning":[118],"support":[120],"this":[121],"capability,":[122],"curate":[124],"IR-600K,":[125],"large-scale":[127],"dataset":[128],"tailored":[129],"for":[130],"learning":[131],"frame-query":[132],"intent":[133],"alignment.Experiments":[134],"show":[135],"VideoStir":[137],"competitive":[139],"stateof-the-art":[141],"baselines":[142],"without":[143],"relying":[144],"auxiliary":[146],"information,":[147],"highlighting":[148],"promise":[150],"of":[151],"shifting":[152],"from":[155],"flattened":[156],"matching":[158],"structured,":[160],"reasoning.Codes":[162],"checkpoints":[164],"available":[166],"https:":[168],"//github.com/RomGai/VideoStir.":[169]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}