{"id":"https://openalex.org/W2896830321","doi":"https://doi.org/10.1109/icme.2018.8486496","title":"Seethevoice: Learning from Music to Visual Storytelling of Shots","display_name":"Seethevoice: Learning from Music to Visual Storytelling of Shots","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2896830321","doi":"https://doi.org/10.1109/icme.2018.8486496","mag":"2896830321"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2018.8486496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2018.8486496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020435776","display_name":"Wen-Li Wei","orcid":"https://orcid.org/0000-0002-6753-2824"},"institutions":[{"id":"https://openalex.org/I4210147455","display_name":"Institute of Information Science","ror":"https://ror.org/055q8rh54","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210147455"]}],"countries":["SI"],"is_corresponding":true,"raw_author_name":"Wen-Li Wei","raw_affiliation_strings":["Institute of Information Science"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science","institution_ids":["https://openalex.org/I4210147455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077668438","display_name":"Jen\u2010Chun Lin","orcid":"https://orcid.org/0000-0002-9237-4119"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Chun Lin","raw_affiliation_strings":["Department of Electrical Engineering, Yuan Ze University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Yuan Ze University, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043386280","display_name":"Tyng-Luh Liu","orcid":"https://orcid.org/0000-0002-8366-5213"},"institutions":[{"id":"https://openalex.org/I4210147455","display_name":"Institute of Information Science","ror":"https://ror.org/055q8rh54","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210147455"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Tyng-Luh Liu","raw_affiliation_strings":["Institute of Information Science"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science","institution_ids":["https://openalex.org/I4210147455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210147455","display_name":"Institute of Information Science","ror":"https://ror.org/055q8rh54","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210147455"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science","institution_ids":["https://openalex.org/I4210147455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006963326","display_name":"Hsiao-Rong Tyan","orcid":null},"institutions":[{"id":"https://openalex.org/I151221077","display_name":"Chung Yuan Christian University","ror":"https://ror.org/02w8ws377","country_code":"TW","type":"education","lineage":["https://openalex.org/I151221077"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiao-Rong Tyan","raw_affiliation_strings":["Dept. of Information and Computer Engineering, Chung Yuan Christian Univ, Taiwan"],"affiliations":[{"raw_affiliation_string":"Dept. of Information and Computer Engineering, Chung Yuan Christian Univ, Taiwan","institution_ids":["https://openalex.org/I151221077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108538229","display_name":"Hong-Yuan Mark Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147455","display_name":"Institute of Information Science","ror":"https://ror.org/055q8rh54","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210147455"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Hong-Yuan Mark Liao","raw_affiliation_strings":["Institute of Information Science"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science","institution_ids":["https://openalex.org/I4210147455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5020435776"],"corresponding_institution_ids":["https://openalex.org/I4210147455"],"apc_list":null,"apc_paid":null,"fwci":0.4178,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67564014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9977999925613403,"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":0.9977999925613403,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9700999855995178,"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":0.7552012205123901},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.7526447772979736},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5959821939468384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4751051366329193},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4743427336215973},{"id":"https://openalex.org/keywords/amateur","display_name":"Amateur","score":0.46550777554512024},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4402278959751129},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.43378400802612305},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35370391607284546},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.13586455583572388},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09463346004486084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7552012205123901},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.7526447772979736},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5959821939468384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4751051366329193},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4743427336215973},{"id":"https://openalex.org/C2778044066","wikidata":"https://www.wikidata.org/wiki/Q455595","display_name":"Amateur","level":2,"score":0.46550777554512024},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4402278959751129},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.43378400802612305},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35370391607284546},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.13586455583572388},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09463346004486084},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2018.8486496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2018.8486496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W357674266","https://openalex.org/W1947481528","https://openalex.org/W1971888092","https://openalex.org/W1976684802","https://openalex.org/W2012966741","https://openalex.org/W2064675550","https://openalex.org/W2069662785","https://openalex.org/W2127870748","https://openalex.org/W2139501017","https://openalex.org/W2144198023","https://openalex.org/W2314395941","https://openalex.org/W2525577390","https://openalex.org/W2685505040","https://openalex.org/W2897807721","https://openalex.org/W2962677625","https://openalex.org/W2964241990","https://openalex.org/W6678969435"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Types":[0],"of":[1,6,53,59,116,132],"shots":[2,26],"in":[3,49],"the":[4,10,34,38,42,60,99,109,129,137,171],"language":[5],"film":[7],"are":[8],"considered":[9],"key":[11],"elements":[12],"used":[13,125],"by":[14,107],"a":[15,22,54,75,85,102,133,145,166],"director":[16],"for":[17,169],"visual":[18,43,114,130],"storytelling.":[19],"In":[20],"filming":[21],"musical":[23],"performance,":[24],"manipulating":[25],"could":[27],"stimulate":[28],"desired":[29],"effects":[30],"such":[31,65,89],"as":[32,151],"manifesting":[33],"emotion":[35],"or":[36],"deepening":[37],"atmosphere.":[39],"However,":[40],"while":[41],"storytelling":[44,115,131],"technique":[45],"is":[46],"often":[47,63],"employed":[48],"creating":[50],"professional":[51],"recordings":[52,58],"live":[55],"concert,":[56],"audience":[57],"same":[61],"event":[62],"lack":[64],"sophisticated":[66],"manipulations.":[67],"Thus":[68],"it":[69],"would":[70],"be":[71,124],"useful":[72],"to":[73,83,97,126],"have":[74],"versatile":[76],"system":[77],"that":[78,182],"can":[79,122,186],"perform":[80],"video":[81,87,139],"mashup":[82,140],"create":[84],"refined":[86],"from":[88,176],"amateur":[90],"clips.":[91],"To":[92],"this":[93],"end,":[94],"we":[95],"propose":[96],"translate":[98],"music":[100,112],"into":[101],"near-professional":[103],"shot":[104,120,190],"(type)":[105],"sequence":[106,121,191],"learning":[108],"relation":[110],"between":[111],"and":[113,135,165,178],"shots.":[117],"The":[118,174],"resulting":[119],"then":[123],"better":[127,193],"portray":[128],"song":[134],"guide":[136],"concert":[138],"process.":[141],"Our":[142],"method":[143],"introduces":[144],"novel":[146],"probabilistic-based":[147],"fusion":[148],"approach,":[149],"named":[150],"multi-resolution":[152,162],"fused":[153,163],"recurrent":[154],"neural":[155],"networks":[156],"(MF-RNNs)":[157],"with":[158,184,192],"film-language,":[159],"which":[160],"integrates":[161],"RNNs":[164],"film-language":[167,185],"model":[168],"boosting":[170],"translation":[172],"performance.":[173],"results":[175],"objective":[177],"subjective":[179],"experiments":[180],"demonstrate":[181],"MF-RNNs":[183],"generate":[187],"an":[188],"appealing":[189],"viewing":[194],"experience.":[195]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
