{"id":"https://openalex.org/W3093272234","doi":"https://doi.org/10.1145/3394171.3413985","title":"Learning From Music to Visual Storytelling of Shots: A Deep Interactive Learning Mechanism","display_name":"Learning From Music to Visual Storytelling of Shots: A Deep Interactive Learning Mechanism","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093272234","doi":"https://doi.org/10.1145/3394171.3413985","mag":"3093272234"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413985","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077668438","display_name":"Jen\u2010Chun Lin","orcid":"https://orcid.org/0000-0002-9237-4119"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Chun Lin","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020435776","display_name":"Wen-Li Wei","orcid":"https://orcid.org/0000-0002-6753-2824"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Li Wei","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002217153","display_name":"Yen\u2010Yu Lin","orcid":"https://orcid.org/0000-0002-7183-6070"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Yu Lin","raw_affiliation_strings":["National Chiao Tung University, Hsinchu, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chiao Tung University, Hsinchu, Taiwan Roc","institution_ids":["https://openalex.org/I148366613"]}]},{"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/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tyng-Luh Liu","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108538229","display_name":"Hong-Yuan Mark Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I177918364","display_name":"Providence University","ror":"https://ror.org/03fcpsq87","country_code":"TW","type":"education","lineage":["https://openalex.org/I177918364"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Yuan Mark Liao","raw_affiliation_strings":["Academia Sinica &amp; Providence University, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica &amp; Providence University, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I177918364","https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9908000230789185,"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":0.9868999719619751,"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":0.7862606644630432},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6234856843948364},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5299333930015564},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.5109102129936218},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.509994626045227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4976990520954132},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4918704032897949},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4734242260456085},{"id":"https://openalex.org/keywords/interactive-storytelling","display_name":"Interactive storytelling","score":0.43841278553009033},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4028978943824768},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3714049160480499},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.0815015435218811}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862606644630432},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6234856843948364},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5299333930015564},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.5109102129936218},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.509994626045227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4976990520954132},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4918704032897949},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4734242260456085},{"id":"https://openalex.org/C2779754051","wikidata":"https://www.wikidata.org/wiki/Q2903135","display_name":"Interactive storytelling","level":4,"score":0.43841278553009033},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4028978943824768},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3714049160480499},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.0815015435218811},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413985","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[{"id":"https://openalex.org/G4970566006","display_name":null,"funder_award_id":"109-2634-F-001-011, 109-2634-F-001-012, 107-2218-E-001-010-MY2, 107-2628-E-009-007-MY3, 109-2634-F-007-013, 109-2221-E-009-113-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W357674266","https://openalex.org/W569478347","https://openalex.org/W1821462560","https://openalex.org/W1976684802","https://openalex.org/W2069662785","https://openalex.org/W2134797427","https://openalex.org/W2183386595","https://openalex.org/W2294370754","https://openalex.org/W2300242332","https://openalex.org/W2525577390","https://openalex.org/W2525579820","https://openalex.org/W2541993794","https://openalex.org/W2559780844","https://openalex.org/W2615063356","https://openalex.org/W2620998106","https://openalex.org/W2685505040","https://openalex.org/W2739879705","https://openalex.org/W2795041432","https://openalex.org/W2809603942","https://openalex.org/W2896830321","https://openalex.org/W2897493023","https://openalex.org/W2932970397","https://openalex.org/W2950359962","https://openalex.org/W2952787292","https://openalex.org/W2962965870","https://openalex.org/W2964118293","https://openalex.org/W2964299589","https://openalex.org/W2976135203","https://openalex.org/W3023742835","https://openalex.org/W3035814330","https://openalex.org/W3093329015","https://openalex.org/W3102424508","https://openalex.org/W4301045096"],"related_works":["https://openalex.org/W206099924","https://openalex.org/W3084032109","https://openalex.org/W1506162009","https://openalex.org/W3135660093","https://openalex.org/W2737901105","https://openalex.org/W2060531897","https://openalex.org/W1999077548","https://openalex.org/W1986086006","https://openalex.org/W1800308398","https://openalex.org/W2528706208"],"abstract_inverted_index":{"Learning":[0],"from":[1,73,154,245],"music":[2],"to":[3,68,129,167,185,189,202],"visual":[4,18],"storytelling":[5,33],"of":[6,23,125,171],"shots":[7],"is":[8,123],"an":[9,100],"interesting":[10],"and":[11,46,85,104,135,162,173,215,218,227,236,251],"emerging":[12],"task.":[13,71],"It":[14,146],"produces":[15,219],"a":[16,24,36,54,62,78,86,105,119,131],"coherent":[17],"story":[19],"in":[20,89,198],"the":[21,32,70,74,93,109,137,149,156,163,169,178,190,195,206,210,213,234,249],"form":[22],"shot":[25,132,243],"type":[26,133],"sequence,":[27],"which":[28],"not":[29],"only":[30],"expands":[31],"potential":[34],"for":[35,60,223],"song":[37],"but":[38],"also":[39,112],"facilitates":[40],"automatic":[41],"concert":[42],"video":[43],"mashup":[44],"process":[45],"storyboard":[47],"generation.":[48],"In":[49],"this":[50],"study,":[51],"we":[52],"present":[53],"deep":[55],"interactive":[56,204],"learning":[57,98],"(DIL)":[58],"mechanism":[59,208],"building":[61],"compact":[63],"yet":[64],"accurate":[65],"sequence-to-sequence":[66],"model":[67],"accomplish":[69],"Different":[72],"one-way":[75],"transfer":[76],"between":[77,99,212],"pre-trained":[79],"teacher":[80,102,120,196,214,235],"network":[81,88,103,111,121,151,180,197],"(or":[82],"ensemble":[83,101],"network)":[84],"student":[87,106,110,150,179,216,237],"knowledge":[90,188],"distillation":[91],"(KD),":[92],"proposed":[94],"method":[95,116],"enables":[96],"collaborative":[97],"network.":[107],"Namely,":[108],"teaches.":[113],"Specifically,":[114],"our":[115],"first":[117],"learns":[118,153],"that":[122,152,232],"composed":[124],"several":[126],"assistant":[127,191],"networks":[128,217,238],"generate":[130,240],"sequence":[134],"produce":[136],"soft":[138,164],"target":[139,165],"(shot":[140],"types)":[141],"distribution":[142,166],"accordingly":[143],"through":[144],"KD.":[145],"then":[147],"constructs":[148],"both":[155,224,233],"ground":[157],"truth":[158],"label":[159],"(hard":[160],"target)":[161],"alleviate":[168],"difficulty":[170],"optimization":[172],"improve":[174],"generalization":[175],"capability.":[176],"As":[177],"gradually":[181],"advances,":[182],"it":[183],"turns":[184],"feed":[186],"back":[187],"networks,":[192],"thereby":[193,247],"improving":[194],"each":[199],"iteration.":[200],"Owing":[201],"such":[203],"designs,":[205],"DIL":[207],"bridges":[209],"gap":[211],"more":[220,241],"superior":[221],"capability":[222],"networks.":[225],"Objective":[226],"subjective":[228],"experimental":[229],"results":[230],"demonstrate":[231],"can":[239],"attractive":[242],"sequences":[244],"music,":[246],"enhancing":[248],"viewing":[250],"listening":[252],"experience.":[253]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
