{"id":"https://openalex.org/W4407230825","doi":"https://doi.org/10.1109/wacv61042.2026.00695","title":"MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding","display_name":"MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4407230825","doi":"https://doi.org/10.1109/wacv61042.2026.00695"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00695","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.03183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076957254","display_name":"Pengyi Li","orcid":"https://orcid.org/0009-0009-8546-2346"},"institutions":[{"id":"https://openalex.org/I4210114044","display_name":"American Xtal Technology (United States)","ror":"https://ror.org/024h4bk68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114044"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengyi Li","raw_affiliation_strings":["AXXX,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AXXX,Russia","institution_ids":["https://openalex.org/I4210114044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095335183","display_name":"Irina Abdullaeva","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114044","display_name":"American Xtal Technology (United States)","ror":"https://ror.org/024h4bk68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114044"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Irina Abdullaeva","raw_affiliation_strings":["AXXX,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AXXX,Russia","institution_ids":["https://openalex.org/I4210114044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093257701","display_name":"Alexander Gambashidze","orcid":"https://orcid.org/0009-0008-0576-9835"},"institutions":[{"id":"https://openalex.org/I4210114044","display_name":"American Xtal Technology (United States)","ror":"https://ror.org/024h4bk68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114044"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Gambashidze","raw_affiliation_strings":["AXXX,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AXXX,Russia","institution_ids":["https://openalex.org/I4210114044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101915268","display_name":"Andrey Kuznetsov","orcid":"https://orcid.org/0000-0002-0425-2171"},"institutions":[{"id":"https://openalex.org/I4210114044","display_name":"American Xtal Technology (United States)","ror":"https://ror.org/024h4bk68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114044"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrey Kuznetsov","raw_affiliation_strings":["AXXX,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AXXX,Russia","institution_ids":["https://openalex.org/I4210114044"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004111307","display_name":"Ivan Oseledets","orcid":"https://orcid.org/0000-0003-2071-2163"},"institutions":[{"id":"https://openalex.org/I4210114044","display_name":"American Xtal Technology (United States)","ror":"https://ror.org/024h4bk68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114044"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Oseledets","raw_affiliation_strings":["AXXX,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AXXX,Russia","institution_ids":["https://openalex.org/I4210114044"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.00418685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7198","last_page":"7207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.998199999332428,"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/T11439","display_name":"Video Analysis and Summarization","score":0.998199999332428,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9980000257492065,"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":0.9958000183105469,"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/selection","display_name":"Selection (genetic algorithm)","score":0.7641576528549194},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7268648743629456},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.7143702507019043},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6442133188247681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6377108097076416},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4964819550514221},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.4835948348045349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40571659803390503},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33454760909080505},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1101655662059784},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08766567707061768},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07571423053741455}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7641576528549194},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7268648743629456},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.7143702507019043},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6442133188247681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377108097076416},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4964819550514221},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.4835948348045349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40571659803390503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33454760909080505},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1101655662059784},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08766567707061768},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07571423053741455},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00695","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:2502.03183","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.03183","pdf_url":"https://arxiv.org/pdf/2502.03183","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2502.03183","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.03183","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":"pmh:oai:arXiv.org:2502.03183","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.03183","pdf_url":"https://arxiv.org/pdf/2502.03183","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"id":"https://openalex.org/F4320324632","display_name":"Ministero dello Sviluppo Economico","ror":"https://ror.org/011z3ff80"},{"id":"https://openalex.org/F4320330527","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407230825.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2810201907","https://openalex.org/W1614340030","https://openalex.org/W2386640596","https://openalex.org/W2103803681","https://openalex.org/W2356908413","https://openalex.org/W2912576419","https://openalex.org/W2036745083","https://openalex.org/W2394559091","https://openalex.org/W2557342721","https://openalex.org/W855007925"],"abstract_inverted_index":{"Modern":[0],"Video":[1],"Large":[2],"Language":[3],"Models":[4],"(VLLMs)":[5],"often":[6],"rely":[7],"on":[8,41,122,128,139,143],"uniform":[9,175],"frame":[10,26],"sampling":[11,176],"for":[12,130,159],"video":[13,31,110],"understanding,":[14],"but":[15],"this":[16],"approach":[17,146],"frequently":[18],"fails":[19],"to":[20,25,149,173],"capture":[21],"critical":[22],"information":[23],"due":[24],"redundancy":[27,95],"and":[28,51,54,60,107,124,141,151,162,170],"variations":[29],"in":[30,49],"content.":[32],"We":[33],"propose":[34],"MaxInfo,":[35],"the":[36,42,62,71,81,85,90,102,157],"first":[37],"training-free":[38],"method":[39,100],"based":[40],"maximum":[43],"volume":[44,73],"principle,":[45],"which":[46],"is":[47,147],"available":[48,181],"Fast":[50],"Slow":[52],"versions":[53],"a":[55,67,119,125,168],"Chunk-based":[56],"version":[57],"that":[58,80],"selects":[59],"retains":[61],"most":[63,86],"representative":[64],"frames":[65,83],"from":[66],"video.":[68],"By":[69],"maximizing":[70],"geometric":[72],"formed":[74],"by":[75,137],"selected":[76],"embeddings,":[77],"MaxInfo":[78,117,133],"ensures":[79],"chosen":[82],"cover":[84],"informative":[87],"regions":[88],"of":[89,104],"embedding":[91],"space,":[92],"effectively":[93],"reducing":[94],"while":[96],"preserving":[97],"diversity.":[98],"This":[99],"enhances":[101],"quality":[103],"input":[105],"representations":[106],"improves":[108],"long":[109],"comprehension":[111],"performance":[112,136],"across":[113],"benchmarks.":[114],"For":[115],"instance,":[116],"achieves":[118],"3.28%":[120],"improvement":[121,127],"LongVideoBench":[123,135],"6.4%":[126],"EgoSchema":[129],"LLaVA-Video-7B.":[131],"Moreover,":[132],"boosts":[134],"3.47%":[138],"LLaVA-Video-72B":[140],"3.44%":[142],"MiniCPM4.5.":[144],"The":[145],"simple":[148],"implement":[150],"works":[152],"with":[153],"existing":[154],"VLLMs":[155],"without":[156],"need":[158],"additional":[160],"training":[161],"very":[163],"lower":[164],"latency,":[165],"making":[166],"it":[167],"practical":[169],"effective":[171],"alternative":[172],"traditional":[174],"methods.":[177],"Our":[178],"code":[179],"are":[180],"at":[182],"https://github.com/FusionBrainLab/MaxInfo.git":[183]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}