{"id":"https://openalex.org/W7163887363","doi":"https://doi.org/10.1145/3788851.3815032","title":"Toward an AI Director: Automating Live Presentations with Local Vision-Language Models","display_name":"Toward an AI Director: Automating Live Presentations with Local Vision-Language Models","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7163887363","doi":"https://doi.org/10.1145/3788851.3815032"},"language":null,"primary_location":{"id":"doi:10.1145/3788851.3815032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788851.3815032","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM International Conference on Interactive Media Experiences","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788851.3815032","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120235753","display_name":"Eugenio Giuseppe Nerelli","orcid":null},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eugenio Giuseppe Nerelli","raw_affiliation_strings":["Department of Informatics, University of Val\u00e8ncia, Val\u00e8ncia, Val\u00e8ncia, Spain"],"raw_orcid":"https://orcid.org/0000-0003-0991-643X","affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Val\u00e8ncia, Val\u00e8ncia, Val\u00e8ncia, Spain","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030839479","display_name":"Alberto Robazza","orcid":"https://orcid.org/0009-0005-0874-3719"},"institutions":[{"id":"https://openalex.org/I129043915","display_name":"University of Udine","ror":"https://ror.org/05ht0mh31","country_code":"IT","type":"education","lineage":["https://openalex.org/I129043915"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Robazza","raw_affiliation_strings":["University of Udine, Udine, Italy"],"raw_orcid":"https://orcid.org/0009-0001-9070-8269","affiliations":[{"raw_affiliation_string":"University of Udine, Udine, Italy","institution_ids":["https://openalex.org/I129043915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138115097","display_name":"Andrea Turchet","orcid":"https://orcid.org/0009-0007-4125-2019"},"institutions":[{"id":"https://openalex.org/I129043915","display_name":"University of Udine","ror":"https://ror.org/05ht0mh31","country_code":"IT","type":"education","lineage":["https://openalex.org/I129043915"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Turchet","raw_affiliation_strings":["University of Udine, Udine, Italy"],"raw_orcid":"https://orcid.org/0009-0007-4125-2019","affiliations":[{"raw_affiliation_string":"University of Udine, Udine, Italy","institution_ids":["https://openalex.org/I129043915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138157824","display_name":"Mario Montagud Climent","orcid":"https://orcid.org/0000-0002-2398-1505"},"institutions":[{"id":"https://openalex.org/I4210130845","display_name":"i2CAT","ror":"https://ror.org/02rkks755","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210130845","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mario Montagud Climent","raw_affiliation_strings":["Department of Informatics, University of Valencia, Valencia, Spain and Media &amp; Internet Area, i2cat Foundation, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-2398-1505","affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Valencia, Valencia, Spain and Media &amp; Internet Area, i2cat Foundation, Barcelona, Spain","institution_ids":["https://openalex.org/I4210130845"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"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":"504","last_page":"508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.24140000343322754,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.24140000343322754,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12031","display_name":"Speech and dialogue systems","score":0.18619999289512634,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1185000017285347,"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/modular-design","display_name":"Modular design","score":0.5719000101089478},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.5435000061988831},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.5364000201225281},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5289999842643738},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5241000056266785},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5113000273704529},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4138000011444092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297000288963318},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5289999842643738},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5241000056266785},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4474000036716461},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43059998750686646},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.39980000257492065},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788851.3815032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788851.3815032","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM International Conference on Interactive Media Experiences","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788851.3815032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788851.3815032","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM International Conference on Interactive Media Experiences","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5695793628692627}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1561304027","https://openalex.org/W4394593134","https://openalex.org/W4407185814","https://openalex.org/W4407638672","https://openalex.org/W4409095658","https://openalex.org/W4409886277","https://openalex.org/W4410915147","https://openalex.org/W4412431580","https://openalex.org/W4413146426","https://openalex.org/W4413948760","https://openalex.org/W4415002974","https://openalex.org/W7115017587","https://openalex.org/W7126076012","https://openalex.org/W7127380250","https://openalex.org/W7131381461","https://openalex.org/W7138237524","https://openalex.org/W7138257303","https://openalex.org/W7160103840"],"related_works":[],"abstract_inverted_index":{"Directing":[0],"a":[1,53,77,82,90,99,134],"live":[2,100],"presentation":[3,119],"involves":[4],"continuous":[5],"decision-making:":[6],"selecting":[7],"which":[8],"camera":[9],"feed":[10,102],"or":[11,46,52],"scene":[12],"to":[13,24,85,109],"display,":[14],"synchronizing":[15],"visual":[16],"content":[17],"with":[18,94,125],"the":[19,25,50,70,111,118,143,147,150],"speaker\u2019s":[20],"narrative,":[21],"and":[22,106,114,153,158],"responding":[23],"presenter\u2019s":[26,112],"actions":[27,113],"in":[28,137],"real":[29],"time.":[30],"In":[31],"many":[32],"settings":[33],"where":[34],"presentations":[35],"occur":[36],"(classrooms,":[37],"seminars,":[38],"webinars,":[39],"videoconferences),":[40],"this":[41,73],"process":[42],"is":[43,131],"either":[44],"absent":[45],"handled":[47],"manually":[48],"by":[49],"presenter":[51],"dedicated":[54],"operator.":[55],"This":[56],"paper":[57,144],"explores":[58],"whether":[59],"multimodal":[60],"AI":[61,88],"techniques,":[62],"executed":[63],"locally":[64],"on":[65,146,156],"consumer":[66],"hardware,":[67],"can":[68],"support":[69],"automation":[71],"of":[72,79,133],"process.":[74],"It":[75],"presents":[76],"proof":[78],"concept":[80],"for":[81],"system":[83,130],"referred":[84],"as":[86],"an":[87],"director:":[89],"modular":[91],"pipeline":[92],"built":[93],"open-source":[95],"components":[96],"that":[97],"processes":[98],"video":[101],"alongside":[103],"audio":[104],"transcription":[105],"gesture":[107],"recognition":[108],"describe":[110],"extract":[115],"information":[116],"from":[117],"content.":[120],"All":[121],"processing":[122],"runs":[123],"on-device,":[124],"no":[126],"cloud":[127],"dependency.":[128],"The":[129],"part":[132],"broader":[135],"work":[136],"progress":[138],"toward":[139],"multi-camera":[140],"automated":[141],"direction;":[142],"reports":[145],"devised":[148],"architecture,":[149],"selected":[151],"components,":[152],"preliminary":[154],"observations":[155],"feasibility":[157],"resource":[159],"constraints.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-09T00:00:00"}
