{"id":"https://openalex.org/W4417196400","doi":"https://doi.org/10.1109/wacv61042.2026.00136","title":"FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs","display_name":"FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417196400","doi":"https://doi.org/10.1109/wacv61042.2026.00136"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00136","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.19850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094581598","display_name":"Carlos Plou","orcid":"https://orcid.org/0009-0004-7535-9955"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Plou","raw_affiliation_strings":["University of Zaragoza,DIIS-I3A,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza,DIIS-I3A,Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cesar Borja","orcid":null},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Cesar Borja","raw_affiliation_strings":["University of Zaragoza,DIIS-I3A,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza,DIIS-I3A,Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049372967","display_name":"Rub\u00e9n Mart\u00ednez-Cant\u00edn","orcid":"https://orcid.org/0000-0002-6741-844X"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ruben Martinez-Cantin","raw_affiliation_strings":["University of Zaragoza,DIIS-I3A,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza,DIIS-I3A,Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074342722","display_name":"Ana C. Murillo","orcid":"https://orcid.org/0000-0002-7580-9037"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ana C. Murillo","raw_affiliation_strings":["University of Zaragoza,DIIS-I3A,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza,DIIS-I3A,Spain","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01357737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1334","last_page":"1344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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":0.9969000220298767,"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":0.000699999975040555,"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/T10028","display_name":"Topic Modeling","score":0.0005000000237487257,"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/generalization","display_name":"Generalization","score":0.6626999974250793},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.654699981212616},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6337000131607056},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6032000184059143},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.589900016784668},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.4948999881744385},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4909000098705292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002999782562256},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6626999974250793},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.654699981212616},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5486000180244446},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4909000098705292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41609999537467957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2745000123977661}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00136","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:2503.19850","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19850","pdf_url":"https://arxiv.org/pdf/2503.19850","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.2503.19850","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.19850","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:2503.19850","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19850","pdf_url":"https://arxiv.org/pdf/2503.19850","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Finding":[0],"information":[1],"in":[2,99,120,128],"hour-long":[3,100],"videos":[4,133],"is":[5],"a":[6,34,40,46,49,104,108],"challenging":[7],"task":[8],"even":[9],"for":[10,96],"top-performing":[11],"Vision":[12],"Language":[13,51],"Models":[14],"(VLMs),":[15],"as":[16],"encoding":[17],"visual":[18],"content":[19],"quickly":[20],"exceeds":[21],"available":[22],"context":[23],"windows.":[24],"To":[25],"tackle":[26],"this":[27],"challenge,":[28],"we":[29],"present":[30],"FALCONEye<sup":[31],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[32],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[33],"novel":[35],"video":[36],"agent":[37],"based":[38],"on":[39,139],"training-free,":[41],"model-agnostic":[42],"meta-architecture":[43],"composed":[44],"of":[45,150],"VLM":[47,106],"and":[48,91,107,117,134],"Large":[50],"Model":[52],"(LLM).":[53],"FALCONEye":[54,111],"answers":[55],"open-ended":[56,97],"questions":[57,98],"using":[58],"an":[59,148],"exploration-based":[60],"search":[61],"algorithm":[62],"guided":[63],"by":[64,146],"calibrated":[65],"confidence":[66],"from":[67],"the":[68,74,89],"VLM\u2019s":[69],"answers.":[70],"We":[71],"also":[72],"introduce":[73],"FALCON-Bench":[75],"benchmark,":[76],"extending":[77],"Question":[78],"Answering":[79],"problem":[80],"to":[81,86],"Video":[82],"Answer":[83],"Search\u2014requiring":[84],"models":[85],"return":[87],"both":[88],"answer":[90],"its":[92,125],"supporting":[93],"temporal":[94],"window":[95],"videos.":[101],"With":[102],"just":[103],"7B":[105,115],"lightweight":[109],"LLM,":[110],"outscores":[112],"all":[113],"open-source":[114],"VLMs":[116],"comparable":[118],"agents":[119],"FALCON-Bench.":[121],"It":[122],"further":[123],"demonstrates":[124],"generalization":[126],"capability":[127],"MLVU":[129],"benchmark":[130],"with":[131],"shorter":[132],"different":[135],"tasks,":[136],"surpassing":[137],"GPT-4o":[138],"single-detail":[140],"tasks":[141],"while":[142],"slashing":[143],"inference":[144],"cost":[145],"roughly":[147],"order":[149],"magnitude.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}