{"id":"https://openalex.org/W4417466313","doi":"https://doi.org/10.1109/wacv61042.2026.00547","title":"KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding","display_name":"KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417466313","doi":"https://doi.org/10.1109/wacv61042.2026.00547"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.14017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016271188","display_name":"Zongyao Li","orcid":"https://orcid.org/0000-0002-3300-1806"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zongyao Li","raw_affiliation_strings":["NEC Corporation,Visual Intelligence Research Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation,Visual Intelligence Research Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028193842","display_name":"KENGO ISHIDA","orcid":"https://orcid.org/0000-0003-3652-8408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kengo Ishida","raw_affiliation_strings":["NEC Corporation,Visual Intelligence Research Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation,Visual Intelligence Research Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776276","display_name":"Satoshi Yamazaki","orcid":"https://orcid.org/0000-0002-0624-8416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Yamazaki","raw_affiliation_strings":["NEC Corporation,Visual Intelligence Research Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation,Visual Intelligence Research Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012317930","display_name":"Xiaotong Ji","orcid":"https://orcid.org/0000-0002-8893-1760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaotong Ji","raw_affiliation_strings":["NEC Corporation,Visual Intelligence Research Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation,Visual Intelligence Research Laboratories","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101615203","display_name":"Jian\u2010Quan Liu","orcid":"https://orcid.org/0000-0002-4773-4250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianquan Liu","raw_affiliation_strings":["NEC Corporation,Visual Intelligence Research Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation,Visual Intelligence Research Laboratories","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"5643","last_page":"5652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8684999942779541,"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":0.8684999942779541,"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":0.04360000044107437,"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/T11439","display_name":"Video Analysis and Summarization","score":0.019700000062584877,"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/key","display_name":"Key (lock)","score":0.7911999821662903},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7603999972343445},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.7039999961853027},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6583999991416931},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6175000071525574},{"id":"https://openalex.org/keywords/sampling-frame","display_name":"Sampling frame","score":0.5597000122070312},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.42820000648498535},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4271000027656555}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7911999821662903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900000214576721},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7603999972343445},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.7039999961853027},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6583999991416931},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6175000071525574},{"id":"https://openalex.org/C198327121","wikidata":"https://www.wikidata.org/wiki/Q7410163","display_name":"Sampling frame","level":3,"score":0.5597000122070312},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5128999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.462799996137619},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.34929999709129333},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.2872999906539917},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C65499552","wikidata":"https://www.wikidata.org/wiki/Q5421061","display_name":"Experience sampling method","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2551000118255615}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.14017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.14017","pdf_url":"https://arxiv.org/pdf/2512.14017","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.14017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.14017","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.14017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.14017","pdf_url":"https://arxiv.org/pdf/2512.14017","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417466313.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"KFS-Bench,":[2,104],"the":[3,59,130,138],"first":[4],"benchmark":[5,195],"for":[6,33],"key":[7,111,131,157,188],"frame":[8,29,68,112,158,189],"sampling":[9,26,30,93,113,120,127,144,159,167,181,190],"in":[10,186],"long":[11,39,101],"video":[12,36,40],"question":[13],"answering":[14],"(QA),":[15],"featuring":[16],"multi-scene":[17],"annotations":[18,77],"to":[19,51,88,165],"enable":[20],"direct":[21],"and":[22,55,115,126,191],"robust":[23],"evaluation":[24],"of":[25,61,78,110,175],"strategies.":[27],"Key":[28],"is":[31,196],"crucial":[32],"efficient":[34],"long-form":[35],"understanding.":[37],"In":[38],"QA,":[41],"selecting":[42],"informative":[43],"frames":[44],"enables":[45],"multimodal":[46],"large":[47],"language":[48],"models":[49],"(MLLMs)":[50],"improve":[52],"both":[53,187],"accuracy":[54],"efficiency.":[56],"KFS-Bench":[57,85],"addresses":[58],"limitation":[60],"prior":[62],"works":[63],"that":[64,117,147,161],"only":[65,119],"indirectly":[66],"assess":[67],"selection":[69],"quality":[70,145],"via":[71],"QA":[72,134,150,192],"accuracy.":[73,151],"By":[74],"providing":[75],"ground-truth":[76],"multiple":[79],"disjoint":[80],"scenes":[81],"required":[82],"per":[83],"question,":[84],"allows":[86],"us":[87],"directly":[89],"analyze":[90],"how":[91],"different":[92],"approaches":[94],"capture":[95],"essential":[96],"content":[97],"across":[98],"an":[99],"entire":[100],"video.":[102],"Using":[103],"we":[105,140,153],"conduct":[106],"a":[107,142,155],"comprehensive":[108],"study":[109],"methods":[114],"identify":[116],"not":[118],"precision":[121],"but":[122],"also":[123],"scene":[124],"coverage":[125,174],"balance":[128,166],"are":[129],"factors":[132],"influencing":[133],"performance.":[135,193],"Regarding":[136],"all":[137],"factors,":[139],"design":[141],"novel":[143,156],"metric":[146],"correlates":[148],"with":[149],"Furthermore,":[152],"develop":[154],"method":[160],"leverages":[162],"question\u2013video":[163],"relevance":[164],"diversity":[168],"against":[169],"question\u2013frame":[170],"similarity,":[171],"thereby":[172],"improving":[173],"relevant":[176],"scenes.":[177],"Our":[178],"adaptively":[179],"balanced":[180],"approach":[182],"achieves":[183],"superior":[184],"performance":[185],"The":[194],"available":[197],"at":[198],"https://github.com/NEC-VID/KFS-Bench.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-18T00:00:00"}