{"id":"https://openalex.org/W4387969490","doi":"https://doi.org/10.1145/3581783.3611878","title":"A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Model","display_name":"A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Model","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969490","doi":"https://doi.org/10.1145/3581783.3611878"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611878","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611878","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611878","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611878","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043898209","display_name":"Panwen Hu","orcid":"https://orcid.org/0000-0001-6183-6598"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panwen Hu","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6183-6598","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077441033","display_name":"Nan Xiao","orcid":"https://orcid.org/0009-0003-0886-9982"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Xiao","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-0886-9982","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103262272","display_name":"Feifei Li","orcid":"https://orcid.org/0009-0006-8098-0265"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifei Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-8098-0265","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007341","display_name":"Yongquan Chen","orcid":"https://orcid.org/0000-0003-2493-6033"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongquan Chen","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2493-6033","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029499523","display_name":"Rui Huang","orcid":"https://orcid.org/0000-0002-7950-1662"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Huang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7950-1662","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6441","last_page":"6450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9995999932289124,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9821000099182129,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9807000160217285,"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":0.8825711607933044},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7690699100494385},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.7584861516952515},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6888372898101807},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5263417959213257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5224503874778748},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4886913597583771},{"id":"https://openalex.org/keywords/non-linear-editing-system","display_name":"Non-linear editing system","score":0.45969170331954956},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45092862844467163},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4501695930957794},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37982916831970215},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.37101423740386963},{"id":"https://openalex.org/keywords/video-capture","display_name":"Video capture","score":0.19114181399345398},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.16949820518493652},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09145146608352661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8825711607933044},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7690699100494385},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.7584861516952515},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6888372898101807},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5263417959213257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5224503874778748},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4886913597583771},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.45969170331954956},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45092862844467163},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4501695930957794},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37982916831970215},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.37101423740386963},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.19114181399345398},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.16949820518493652},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09145146608352661},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611878","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611878","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611878","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3611878","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611878","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611878","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969490.pdf","grobid_xml":"https://content.openalex.org/works/W4387969490.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1971888092","https://openalex.org/W1974830671","https://openalex.org/W2000224299","https://openalex.org/W2002954082","https://openalex.org/W2012966741","https://openalex.org/W2025909510","https://openalex.org/W2044961804","https://openalex.org/W2054769378","https://openalex.org/W2069662785","https://openalex.org/W2074520446","https://openalex.org/W2074636075","https://openalex.org/W2101357796","https://openalex.org/W2105296407","https://openalex.org/W2144080233","https://openalex.org/W2145256756","https://openalex.org/W2151103935","https://openalex.org/W2163904290","https://openalex.org/W2294706300","https://openalex.org/W2436270489","https://openalex.org/W2738077708","https://openalex.org/W2799306936","https://openalex.org/W2963155035","https://openalex.org/W2963343921","https://openalex.org/W2999798211","https://openalex.org/W3003268826","https://openalex.org/W3048609641","https://openalex.org/W3136906902","https://openalex.org/W3184970013","https://openalex.org/W3200033334","https://openalex.org/W3211461682","https://openalex.org/W4206059703","https://openalex.org/W4210895630","https://openalex.org/W4235375376","https://openalex.org/W4304014690"],"related_works":["https://openalex.org/W2017202843","https://openalex.org/W2355051182","https://openalex.org/W3095125670","https://openalex.org/W4389713802","https://openalex.org/W4206059703","https://openalex.org/W4210895630","https://openalex.org/W4234065217","https://openalex.org/W2321056253","https://openalex.org/W181158829","https://openalex.org/W4384652403"],"abstract_inverted_index":{"In":[0,76],"this":[1,77],"era":[2],"of":[3,175,184],"videos,":[4],"automatic":[5,31,44,121],"video":[6],"editing":[7,32,53,68,108,133,138,149,161,187],"techniques":[8],"attract":[9],"more":[10,12,159],"and":[11,16,23,58,64,119,140,173,180],"attention":[13],"from":[14],"industry":[15],"academia":[17],"since":[18],"they":[19],"can":[20],"reduce":[21],"workloads":[22],"lower":[24],"the":[25,43,66,97,104,113,116,120,137,142,154,171,176,181],"requirements":[26],"for":[27,46,84],"human":[28],"editors.":[29],"Existing":[30],"systems":[33,45],"are":[34],"mainly":[35],"scene-or":[36],"event-specific,":[37],"e.g.,":[38,49],"soccer":[39],"game":[40],"broadcasting,":[41],"yet":[42],"general":[47,72,85,160],"editing,":[48],"movie":[50,166],"or":[51],"vlog":[52],"which":[54],"covers":[55],"various":[56],"scenes":[57],"events,":[59],"were":[60],"rarely":[61],"studied":[62],"before,":[63],"converting":[65],"event-driven":[67],"method":[69,156],"to":[70,102,111,135,145],"a":[71,81,129,158,164],"scene":[73],"is":[74],"nontrivial.":[75],"paper,":[78],"we":[79,95,127,152],"propose":[80,128],"two-stage":[82],"scheme":[83],"editing.":[86],"Firstly,":[87],"unlike":[88],"previous":[89],"works":[90],"that":[91],"extract":[92,103],"scene-specific":[93],"features,":[94],"leverage":[96],"pre-trained":[98],"Vision-Language":[99],"Model":[100],"(VLM)":[101],"editing-relevant":[105],"representations":[106],"as":[107],"context.":[109],"Moreover,":[110],"close":[112],"gap":[114],"between":[115],"professional-looking":[117],"videos":[118],"productions":[122],"generated":[123],"with":[124,163],"simple":[125],"guidelines,":[126],"Reinforcement":[130],"Learning":[131],"(RL)-based":[132],"framework":[134],"formulate":[136],"problem":[139],"train":[141],"virtual":[143],"editor":[144],"make":[146],"better":[147],"sequential":[148],"decisions.":[150],"Finally,":[151],"evaluate":[153],"proposed":[155,177],"on":[157],"task":[162],"real":[165],"dataset.":[167],"Experimental":[168],"results":[169],"demonstrate":[170],"effectiveness":[172],"benefits":[174],"context":[178],"representation":[179],"learning":[182],"ability":[183],"our":[185],"RL-based":[186],"framework.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}