{"id":"https://openalex.org/W7133335424","doi":"https://doi.org/10.48550/arxiv.2603.00983","title":"Event-Anchored Frame Selection for Effective Long-Video Understanding","display_name":"Event-Anchored Frame Selection for Effective Long-Video Understanding","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7133335424","doi":"https://doi.org/10.48550/arxiv.2603.00983"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00983","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128023124","display_name":"Wang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112987153","display_name":"Yongdong Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yongdong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127883592","display_name":"Yuhui Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Yuhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010577514","display_name":"Luojun Lin","orcid":"https://orcid.org/0000-0002-1141-2487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Luojun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127948713","display_name":"Tianyu Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Tianyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128010984","display_name":"Fei Chao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao, Fei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127974902","display_name":"Rongrong Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Rongrong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zheng, Xiawu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xiawu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5128023124"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.7868000268936157,"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":0.7868000268936157,"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":0.057500001043081284,"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":0.052299998700618744,"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/redundancy","display_name":"Redundancy (engineering)","score":0.6766999959945679},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6116999983787537},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.572700023651123},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5120000243186951},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5110999941825867},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4975999891757965},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.47940000891685486},{"id":"https://openalex.org/keywords/residual-frame","display_name":"Residual frame","score":0.385699987411499},{"id":"https://openalex.org/keywords/semantic-heterogeneity","display_name":"Semantic heterogeneity","score":0.37709999084472656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975999712944031},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6766999959945679},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6116999983787537},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5184999704360962},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5120000243186951},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.47940000891685486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4004000127315521},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.385699987411499},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.37709999084472656},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00983","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00983","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[{"score":0.4375421106815338,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Massive":[0],"frame":[1,9,82],"redundancy":[2],"and":[3,120,155,160],"limited":[4],"context":[5],"window":[6],"make":[7],"efficient":[8],"selection":[10],"crucial":[11],"for":[12,70,115],"long-video":[13],"understanding":[14,142],"with":[15],"large":[16],"vision-language":[17],"models":[18],"(LVLMs).":[19],"Prevailing":[20],"approaches,":[21],"however,":[22],"adopt":[23],"a":[24,47,94,124],"flat":[25],"sampling":[26],"paradigm":[27],"which":[28,66],"treats":[29],"the":[30,58,79,109],"video":[31,59,141],"as":[32,68,83,89],"an":[33,84,99],"unstructured":[34],"collection":[35],"of":[36],"frames.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"introduce":[42],"Event-Anchored":[43],"Frame":[44],"Selection":[45],"(EFS),":[46],"hierarchical,":[48],"event-aware":[49],"pipeline.":[50],"Leveraging":[51],"self-supervised":[52],"DINO":[53],"embeddings,":[54],"EFS":[55,128,149],"first":[56],"partitions":[57],"stream":[60],"into":[61,133],"visually":[62],"homogeneous":[63],"temporal":[64],"segments,":[65],"serve":[67],"proxies":[69],"semantic":[71],"events.":[72],"Within":[73],"each":[74],"event,":[75],"it":[76],"then":[77],"selects":[78],"most":[80],"query-relevant":[81],"anchor.":[85],"These":[86],"anchors":[87],"act":[88],"structural":[90],"priors":[91],"that":[92],"guide":[93],"global":[95],"refinement":[96],"stage":[97],"using":[98],"adaptive":[100],"Maximal":[101],"Marginal":[102],"Relevance":[103],"(MMR)":[104],"scheme.":[105],"This":[106],"pipeline":[107],"ensures":[108],"final":[110],"keyframe":[111],"set":[112],"jointly":[113],"optimizes":[114],"event":[116],"coverage,":[117],"query":[118],"relevance,":[119],"visual":[121],"diversity.":[122],"As":[123],"training-free,":[125],"plug-and-play":[126],"module,":[127],"can":[129],"be":[130],"seamlessly":[131],"integrated":[132],"off-the-shelf":[134],"LVLMs,":[135],"yielding":[136],"substantial":[137],"gains":[138],"on":[139,157],"challenging":[140],"benchmarks.":[143],"Specifically,":[144],"when":[145],"applied":[146],"to":[147],"LLaVA-Video-7B,":[148],"improves":[150],"accuracy":[151],"by":[152],"4.7%,":[153],"4.9%,":[154],"8.8%":[156],"VideoMME,":[158],"LongVideoBench,":[159],"MLVU,":[161],"respectively.":[162]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-03-04T00:00:00"}