{"id":"https://openalex.org/W7138058884","doi":"https://doi.org/10.1609/aaai.v40i6.42406","title":"APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval","display_name":"APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138058884","doi":"https://doi.org/10.1609/aaai.v40i6.42406"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i6.42406","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42406","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42406/46367","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42406/46367","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129707644","display_name":"Hong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Gao","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing 210096, China\nZTE Corporation, Nanjing 210012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing 210096, China\nZTE Corporation, Nanjing 210012, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129750276","display_name":"Yiming Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Bao","raw_affiliation_strings":["ZTE Corporation, Nanjing 210012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZTE Corporation, Nanjing 210012, China","institution_ids":["https://openalex.org/I4210098582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033126589","display_name":"Xuezhen Tu","orcid":"https://orcid.org/0009-0000-3749-5519"},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuezhen Tu","raw_affiliation_strings":["ZTE Corporation, Nanjing 210012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZTE Corporation, Nanjing 210012, China","institution_ids":["https://openalex.org/I4210098582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129657415","display_name":"Bin Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhong","raw_affiliation_strings":["ZTE Corporation, Nanjing 210012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZTE Corporation, Nanjing 210012, China","institution_ids":["https://openalex.org/I4210098582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039145454","display_name":"Linan Yue","orcid":"https://orcid.org/0000-0002-5980-6098"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linan Yue","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing 210096, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing 210096, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129723213","display_name":"Min-Ling Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min-Ling Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing 210096, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing 210096, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.24590067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"6","first_page":"4113","last_page":"4121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9646999835968018,"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":0.9646999835968018,"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":0.007799999788403511,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.004600000102072954,"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/security-token","display_name":"Security token","score":0.5526999831199646},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4943999946117401},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4819999933242798},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4433000087738037},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4124000072479248},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.37459999322891235},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.35830000042915344},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3476000130176544},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.3440999984741211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210999965667725},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4830999970436096},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4819999933242798},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3440000116825104},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i6.42406","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42406","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42406/46367","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42406","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42406","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42406/46367","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138058884.pdf","grobid_xml":"https://content.openalex.org/works/W7138058884.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"multimodal":[1],"large":[2],"language":[3],"models":[4],"(MLLMs)":[5],"struggle":[6],"with":[7],"hour-level":[8],"video":[9,111],"understanding,":[10],"facing":[11],"significant":[12,150],"challenges":[13],"not":[14],"only":[15],"in":[16,27],"modeling":[17],"the":[18,29,59,89,133],"substantial":[19],"information":[20,57,71],"volume":[21],"of":[22,135],"long":[23],"videos":[24,137],"but":[25],"also":[26],"overcoming":[28],"memory":[30,90],"wall":[31,91],"and":[32,38,80,83,103,113,157,162,172],"resource":[33,46],"constraints":[34],"during":[35],"both":[36,170],"training":[37],"inference.":[39],"Although":[40],"recent":[41],"training-free":[42,75,171],"approaches":[43],"have":[44],"alleviated":[45],"demands":[47],"by":[48],"compressing":[49],"visual":[50,56,85],"features,":[51],"their":[52],"reliance":[53],"on":[54,144,159],"incomplete":[55],"limits":[58],"performance":[60,151],"potential.":[61],"To":[62],"address":[63],"these":[64],"limitations,":[65],"we":[66],"propose":[67],"Adaptive":[68],"Pivot":[69,97,114],"Visual":[70],"Retrieval":[72,99,116],"(APVR),":[73],"a":[74],"framework":[76],"that":[77],"hierarchically":[78],"retrieves":[79],"retains":[81],"sufficient":[82],"important":[84],"information.":[86],"It":[87],"breakthroughs":[88],"limitation":[92],"via":[93],"two":[94],"complementary":[95],"components:":[96],"Frame":[98],"employs":[100],"query":[101],"expansion":[102],"iterative":[104],"spatio-semantic":[105],"confidence":[106],"scoring":[107],"to":[108,124,154],"identify":[109],"relevant":[110],"frames,":[112],"Token":[115],"performs":[117],"query-aware":[118],"attention-driven":[119],"token":[120],"selection":[121],"within":[122],"up":[123,153],"1024":[125],"pivot":[126],"frames.":[127],"This":[128],"dual":[129],"granularity":[130],"approach":[131],"enables":[132],"processing":[134],"hour-long":[136],"while":[138],"maintaining":[139],"semantic":[140],"fidelity.":[141],"Experimental":[142],"validations":[143],"three":[145],"different":[146],"baseline":[147],"MLLMs":[148],"demonstrate":[149],"improvements":[152],"9.5%,":[155],"4.6%":[156],"9.7%":[158],"LongVideoBench,":[160],"VideoMME":[161],"MLVU,":[163],"respectively.":[164],"APVR":[165],"achieves":[166],"state-of-the-art":[167],"results":[168],"for":[169],"training-based":[173],"approaches.":[174]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}