{"id":"https://openalex.org/W2527573165","doi":"https://doi.org/10.1145/2964284.2967245","title":"Automatic Music Video Generation Based on Emotion-Oriented Pseudo Song Prediction and Matching","display_name":"Automatic Music Video Generation Based on Emotion-Oriented Pseudo Song Prediction and Matching","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2527573165","doi":"https://doi.org/10.1145/2964284.2967245","mag":"2527573165"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2967245","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","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/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":true,"raw_author_name":"Jen-Chun Lin","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"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"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"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":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077668438"],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":0.7565,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.7236513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"372","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.995199978351593,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7635418176651001},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6466914415359497},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5960435271263123},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5746787190437317},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5738400220870972},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5562058687210083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4952014982700348},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4744637608528137},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4219762980937958},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.4209052324295044},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.255973219871521},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08509057760238647},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08151140809059143},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06929820775985718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635418176651001},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6466914415359497},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5960435271263123},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5746787190437317},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5738400220870972},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5562058687210083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952014982700348},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4744637608528137},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4219762980937958},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.4209052324295044},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.255973219871521},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08509057760238647},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08151140809059143},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06929820775985718},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2967245","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":20,"referenced_works":["https://openalex.org/W1982145483","https://openalex.org/W2002055708","https://openalex.org/W2014281092","https://openalex.org/W2025401819","https://openalex.org/W2031777151","https://openalex.org/W2039583460","https://openalex.org/W2082406456","https://openalex.org/W2095005467","https://openalex.org/W2116777898","https://openalex.org/W2135933687","https://openalex.org/W2144198023","https://openalex.org/W2147776527","https://openalex.org/W2148635594","https://openalex.org/W2148764920","https://openalex.org/W2152491694","https://openalex.org/W2341514930","https://openalex.org/W2343758848","https://openalex.org/W2394773966","https://openalex.org/W2913340405","https://openalex.org/W3217467030"],"related_works":["https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218","https://openalex.org/W2509366663"],"abstract_inverted_index":{"The":[0,144],"main":[1],"difficulty":[2],"in":[3,10,105],"automatic":[4],"music":[5,103,107],"video":[6,18],"(MV)":[7],"generation":[8,28],"lies":[9],"how":[11],"to":[12,46,69,85,110],"match":[13],"two":[14],"different":[15],"media":[16],"(i.e.,":[17],"and":[19,36,54,129,139,148,159,167],"music).":[20],"This":[21],"paper":[22],"proposes":[23],"a":[24,40,62,111],"novel":[25],"content-based":[26],"MV":[27,59,142],"system":[29],"based":[30],"on":[31,126],"emotion-oriented":[32],"pseudo":[33,82,90,130],"song":[34,83],"prediction":[35],"matching.":[37],"We":[38],"use":[39],"multi-task":[41],"deep":[42,113,121],"neural":[43,122],"network":[44,123],"(MDNN)":[45],"jointly":[47],"learn":[48],"the":[49,65,71,76,81,86,89,97,106,127,134,153],"relationship":[50],"among":[51],"music,":[52],"video,":[53,64],"emotion":[55],"from":[56,75],"an":[57],"emotion-annotated":[58],"corpus.":[60],"Given":[61],"queried":[63],"MDNN":[66],"is":[67],"applied":[68],"predict":[70],"acoustic":[72,91,98,128,131],"(music)":[73,92,99],"features":[74,93,100,132],"visual":[77],"(video)":[78],"features,":[79],"i.e.,":[80],"corresponding":[84],"video.":[87],"Then,":[88],"are":[94],"matched":[95],"with":[96,164],"of":[101,133,146],"each":[102],"track":[104],"collection":[108],"according":[109],"pseudo-song-based":[112,155],"similarity":[114],"matching":[115],"(PDSM)":[116],"metric":[117],"given":[118],"by":[119],"another":[120],"(DNN)":[124],"trained":[125],"positive":[135],"(official),":[136],"less-positive":[137],"(artificial),":[138],"negative":[140],"(artificial)":[141],"examples.":[143],"results":[145],"objective":[147],"subjective":[149],"experiments":[150],"demonstrate":[151],"that":[152],"proposed":[154],"framework":[156],"performs":[157],"well":[158],"can":[160],"generate":[161],"appealing":[162],"MVs":[163],"better":[165],"viewing":[166],"listening":[168],"experiences.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}