{"id":"https://openalex.org/W7201836626","doi":"https://doi.org/10.48550/arxiv.2608.05707","title":"One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding","display_name":"One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding","publication_year":2026,"publication_date":"2026-08-06","ids":{"openalex":"https://openalex.org/W7201836626","doi":"https://doi.org/10.48550/arxiv.2608.05707"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.05707","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05707","pdf_url":"https://arxiv.org/pdf/2608.05707","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.05707","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128023124","display_name":"Wang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chen, Wang","raw_affiliation_strings":["Amap , Alibaba Group , China","Media Analytics and Computing Lab , Xiamen University , Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amap , Alibaba Group , China","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"raw_affiliation_string":"Media Analytics and Computing Lab , Xiamen University , Xiamen , China","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146060683","display_name":"Yu Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chen, Yu","raw_affiliation_strings":["Amap , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amap , Alibaba Group , China","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122334324","display_name":"Xiang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wang, Xiang","raw_affiliation_strings":["Amap , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amap , Alibaba Group , China","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146048050","display_name":"Shuai Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Li, Shuai","raw_affiliation_strings":["Amap , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amap , Alibaba Group , China","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947034","display_name":"Jinfa Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Jinfa","raw_affiliation_strings":["Department of Computer Science , University of Rochester , Rochester , NY , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Rochester , Rochester , NY , USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054226277","display_name":"Xiawu Zheng","orcid":"https://orcid.org/0000-0002-6855-5403","observed_orcids":["https://orcid.org/0000-0002-6855-5403"]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Xiawu","raw_affiliation_strings":["Media Analytics and Computing Lab , Xiamen University , Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Analytics and Computing Lab , Xiamen University , Xiamen , China","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9887999892234802,"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":0.9887999892234802,"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":0.008299999870359898,"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":0.0008999999845400453,"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/frame-selection","display_name":"frame selection","score":0.7919999957084656},{"id":"https://openalex.org/keywords/long-video-understanding","display_name":"long video understanding","score":0.824999988079071},{"id":"https://openalex.org/keywords/large-multimodal-models","display_name":"large multimodal models","score":0.7509999871253967},{"id":"https://openalex.org/keywords/temporal-context","display_name":"temporal context","score":0.7120000123977661},{"id":"https://openalex.org/keywords/video-summarization","display_name":"video summarization","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491000294685364},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593000113964081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45489999651908875},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.40380001068115234},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3718999922275543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C198327121","wikidata":"https://www.wikidata.org/wiki/Q7410163","display_name":"Sampling frame","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.05707","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05707","pdf_url":"https://arxiv.org/pdf/2608.05707","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.05707","doi":"https://doi.org/10.48550/arxiv.2608.05707","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.05707","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.05707","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05707","pdf_url":"https://arxiv.org/pdf/2608.05707","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/17","score":0.4729059338569641,"display_name":"Partnerships for the goals"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7201836626.pdf","grobid_xml":"https://content.openalex.org/works/W7201836626.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204881861","https://openalex.org/W7223082384","https://openalex.org/W7169806139","https://openalex.org/W7140085672","https://openalex.org/W4415918554","https://openalex.org/W7213221792","https://openalex.org/W7208838794","https://openalex.org/W7216547966","https://openalex.org/W7172536034","https://openalex.org/W7201847673"],"abstract_inverted_index":{"Frame":[0,155],"selection":[1,100,235],"is":[2,134],"essential":[3],"for":[4,53],"applying":[5],"Large":[6],"Multimodal":[7],"Models":[8],"(LMMs)":[9],"to":[10,14,203],"long":[11,140],"videos":[12,141],"due":[13],"severe":[15],"frame":[16,25,51,99,216],"redundancy":[17],"and":[18,34,93,124,142,172,175,214,232],"limited":[19],"context":[20],"windows.":[21],"Since":[22],"the":[23,29,58,81,88,209],"appropriate":[24],"budget":[26,59,206],"varies":[27],"with":[28],"downstream":[30],"LMM,":[31],"reasoning":[32],"demands,":[33],"latency":[35,236],"constraints,":[36],"a":[37,102,107,132,157,162,178],"practical":[38],"selector":[39],"should":[40],"serve":[41],"multiple":[42],"budgets.":[43],"However,":[44],"existing":[45],"methods":[46],"typically":[47],"optimize":[48],"an":[49],"isolated":[50],"subset":[52],"each":[54],"predefined":[55],"budget:":[56],"when":[57],"changes,":[60],"previously":[61],"selected":[62],"evidence":[63,123],"may":[64],"be":[65,201],"replaced":[66],"rather":[67],"than":[68],"progressively":[69,118,188],"augmented.":[70],"A":[71,196],"fixed-weight":[72],"ranking":[73,104,133,180,198],"allows":[74],"prefix":[75],"reuse":[76],"across":[77],"budgets":[78],"but":[79],"applies":[80],"same":[82],"weighting":[83],"at":[84],"every":[85],"position,":[86],"overlooking":[87],"distinct":[89],"roles":[90],"of":[91],"early":[92,182],"later":[94,186],"ranks.":[95],"We":[96,149],"formulate":[97],"long-video":[98],"as":[101,137],"Matryoshka":[103,152],"problem:":[105],"constructing":[106,130],"single":[108,197],"priority":[109],"sequence":[110],"whose":[111],"small":[112],"prefixes":[113,120],"concentrate":[114],"query-conditioned":[115],"evidence,":[116],"while":[117,192],"larger":[119],"preserve":[121],"this":[122],"add":[125],"broader":[126],"temporal":[127,190],"context.":[128],"Efficiently":[129],"such":[131],"itself":[135],"challenging,":[136],"densely":[138],"sampling":[139,224],"evaluating":[143],"frame-query":[144],"relevance":[145],"incurs":[146],"substantial":[147],"overhead.":[148],"therefore":[150],"introduce":[151],"Evidence-to-Context":[153],"(MEC)":[154],"Selection,":[156],"training-free":[158],"framework":[159],"that":[160],"builds":[161],"reusable":[163],"sparse":[164,170],"video":[165],"index,":[166],"discovers":[167],"candidates":[168],"through":[169],"probing":[171],"local":[173],"zooming,":[174],"greedily":[176],"constructs":[177],"position-adaptive":[179],"-":[181],"positions":[183,187],"emphasize":[184],"evidence;":[185],"favor":[189],"coverage":[191],"preserving":[193],"visual":[194],"diversity.":[195],"can":[199],"thus":[200],"truncated":[202],"any":[204],"target":[205],"without":[207],"rerunning":[208],"selector.":[210],"Across":[211],"four":[212],"benchmarks":[213],"six":[215],"budgets,":[217],"MEC":[218],"improves":[219],"average":[220],"accuracy":[221],"over":[222],"uniform":[223],"by":[225,237],"3.77":[226],"points,":[227],"matches":[228],"strong":[229],"state-of-the-art":[230],"selectors,":[231],"reduces":[233],"end-to-end":[234],"47.37-51.19%.":[238]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-08T00:00:00"}