{"id":"https://openalex.org/W4391940619","doi":"https://doi.org/10.1145/3640543.3645143","title":"LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing","display_name":"LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4391940619","doi":"https://doi.org/10.1145/3640543.3645143"},"language":"en","primary_location":{"id":"doi:10.1145/3640543.3645143","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645143","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645143","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101432451","display_name":"Bryan Wang","orcid":"https://orcid.org/0000-0001-9016-038X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Bryan Wang","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9016-038X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750716","display_name":"Yuliang Li","orcid":"https://orcid.org/0000-0002-0602-149X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuliang Li","raw_affiliation_strings":["Reality Lab Research, Meta, United States"],"raw_orcid":"https://orcid.org/0000-0002-0602-149X","affiliations":[{"raw_affiliation_string":"Reality Lab Research, Meta, United States","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076488365","display_name":"Zhaoyang Lv","orcid":"https://orcid.org/0000-0002-7788-9982"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaoyang Lv","raw_affiliation_strings":["Meta Reality Labs Research, Meta, United States"],"raw_orcid":"https://orcid.org/0000-0002-7788-9982","affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Meta, United States","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016819583","display_name":"Haijun Xia","orcid":"https://orcid.org/0000-0002-9425-0881"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haijun Xia","raw_affiliation_strings":["Department of Cognitive Science and Design Lab, University of California, San Diego, United States"],"raw_orcid":"https://orcid.org/0000-0002-9425-0881","affiliations":[{"raw_affiliation_string":"Department of Cognitive Science and Design Lab, University of California, San Diego, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064730192","display_name":"Yan Xu","orcid":"https://orcid.org/0009-0005-3890-9847"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Xu","raw_affiliation_strings":["Reality Labs Research, Meta, United States"],"raw_orcid":"https://orcid.org/0009-0005-3890-9847","affiliations":[{"raw_affiliation_string":"Reality Labs Research, Meta, United States","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018987835","display_name":"Raj S. Sodhi","orcid":"https://orcid.org/0000-0003-0174-1604"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raj Sodhi","raw_affiliation_strings":["Facebook Reality Labs, Facebook, United States"],"raw_orcid":"https://orcid.org/0009-0004-8729-1791","affiliations":[{"raw_affiliation_string":"Facebook Reality Labs, Facebook, United States","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101432451"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":58.8342,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.99930173,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"699","last_page":"714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11197","display_name":"Digital Games and Media","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11197","display_name":"Digital Games and Media","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.982200026512146,"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":0.9793999791145325,"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/computer-science","display_name":"Computer science","score":0.8392974138259888},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7655279636383057},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6163866519927979},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6078859567642212},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5760354995727539},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.5627329349517822},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.48069697618484497},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4548705816268921},{"id":"https://openalex.org/keywords/creativity","display_name":"Creativity","score":0.4542643427848816},{"id":"https://openalex.org/keywords/non-linear-editing-system","display_name":"Non-linear editing system","score":0.44147640466690063},{"id":"https://openalex.org/keywords/collaborative-editing","display_name":"Collaborative editing","score":0.41167110204696655},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2908004820346832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1746809482574463},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1425984501838684},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10221651196479797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392974138259888},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7655279636383057},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6163866519927979},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6078859567642212},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5760354995727539},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.5627329349517822},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.48069697618484497},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4548705816268921},{"id":"https://openalex.org/C11012388","wikidata":"https://www.wikidata.org/wiki/Q170658","display_name":"Creativity","level":2,"score":0.4542643427848816},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.44147640466690063},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.41167110204696655},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2908004820346832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1746809482574463},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1425984501838684},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10221651196479797},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3640543.3645143","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645143","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645143","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.10294","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.10294","pdf_url":"https://arxiv.org/pdf/2402.10294","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.10294","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.10294","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:10.1145/3640543.3645143","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645143","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645143","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391940619.pdf","grobid_xml":"https://content.openalex.org/works/W4391940619.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2087641817","https://openalex.org/W2532670842","https://openalex.org/W2896010852","https://openalex.org/W2916904544","https://openalex.org/W2917914520","https://openalex.org/W2919674582","https://openalex.org/W2941231575","https://openalex.org/W2960274051","https://openalex.org/W2978041822","https://openalex.org/W2988785632","https://openalex.org/W3009471069","https://openalex.org/W3013998503","https://openalex.org/W3031000691","https://openalex.org/W3047508744","https://openalex.org/W3093699630","https://openalex.org/W3093732029","https://openalex.org/W3094385957","https://openalex.org/W3123393030","https://openalex.org/W3162594825","https://openalex.org/W3173798466","https://openalex.org/W3198965420","https://openalex.org/W4220793291","https://openalex.org/W4220867331","https://openalex.org/W4221055872","https://openalex.org/W4223512253","https://openalex.org/W4225012671","https://openalex.org/W4238155858","https://openalex.org/W4288086169","https://openalex.org/W4292243186","https://openalex.org/W4293792253","https://openalex.org/W4307475423","https://openalex.org/W4307475428","https://openalex.org/W4322759491","https://openalex.org/W4366495671","https://openalex.org/W4366547384","https://openalex.org/W4366548330","https://openalex.org/W4366549767","https://openalex.org/W4383682679","https://openalex.org/W4385572377","https://openalex.org/W4390874280","https://openalex.org/W4399917664"],"related_works":["https://openalex.org/W2787002358","https://openalex.org/W3095125670","https://openalex.org/W2355051182","https://openalex.org/W1025479421","https://openalex.org/W2277254704","https://openalex.org/W647674209","https://openalex.org/W4225137887","https://openalex.org/W2017202843","https://openalex.org/W2321056253","https://openalex.org/W3188919927"],"abstract_inverted_index":{"Video":[0],"creation":[1],"has":[2],"become":[3],"increasingly":[4],"popular,":[5],"yet":[6],"the":[7,24,32,65,70,74,85,90,109,149,174],"expertise":[8],"and":[9,55,79,93,117,154,160],"effort":[10],"required":[11],"for":[12,64,72],"editing":[13,34,57,82,88,152],"often":[14],"pose":[15],"barriers":[16],"to":[17,36,76,97,104,134,172],"beginners.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22,168],"explore":[23],"integration":[25],"of":[26,121,148,162,177],"large":[27],"language":[28,62],"models":[29],"(LLMs)":[30],"into":[31],"video":[33],"workflow":[35],"reduce":[37],"these":[38,166],"barriers.":[39],"Our":[40,124],"design":[41,170],"vision":[42],"is":[43],"embodied":[44],"in":[45,81],"LAVE,":[46],"a":[47],"novel":[48],"system":[49],"that":[50],"provides":[51,87],"LLM-powered":[52],"agent":[53,91,110,122],"assistance":[54],"language-augmented":[56],"features.":[58],"LAVE":[59,101],"automatically":[60],"generates":[61],"descriptions":[63],"user\u2019s":[66],"footage,":[67],"serving":[68],"as":[69],"foundation":[71],"enabling":[73,118],"LLM":[75],"process":[77],"videos":[78,106],"assist":[80],"tasks.":[83],"When":[84],"user":[86,125,146],"objectives,":[89],"plans":[92],"executes":[94],"relevant":[95],"actions":[96],"fulfill":[98],"them.":[99],"Moreover,":[100],"allows":[102],"users":[103],"edit":[105],"through":[107],"either":[108],"or":[111],"direct":[112],"UI":[113],"manipulation,":[114],"providing":[115],"flexibility":[116],"manual":[119],"refinement":[120],"actions.":[123],"study,":[126],"which":[127],"included":[128],"eight":[129],"participants":[130],"ranging":[131],"from":[132],"novices":[133],"proficient":[135],"editors,":[136],"demonstrated":[137],"LAVE\u2019s":[138],"effectiveness.":[139],"The":[140],"results":[141],"also":[142],"shed":[143],"light":[144],"on":[145,157,165],"perceptions":[147],"proposed":[150],"LLM-assisted":[151],"paradigm":[153],"its":[155],"impact":[156],"users\u2019":[158],"creativity":[159],"sense":[161],"co-creation.":[163],"Based":[164],"findings,":[167],"propose":[169],"implications":[171],"inform":[173],"future":[175],"development":[176],"agent-assisted":[178],"content":[179],"editing.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":41},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2024-02-20T00:00:00"}