{"id":"https://openalex.org/W4386302151","doi":"https://doi.org/10.1145/3586183.3606757","title":"Automated Conversion of Music Videos into Lyric Videos","display_name":"Automated Conversion of Music Videos into Lyric Videos","publication_year":2023,"publication_date":"2023-10-20","ids":{"openalex":"https://openalex.org/W4386302151","doi":"https://doi.org/10.1145/3586183.3606757"},"language":"en","primary_location":{"id":"doi:10.1145/3586183.3606757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3586183.3606757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.14922","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089941596","display_name":"Jiaju Ma","orcid":"https://orcid.org/0000-0003-2880-8506"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiaju Ma","raw_affiliation_strings":["Department of Computer Science, Stanford University, United States and Adobe Research, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, United States and Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067715162","display_name":"Anyi Rao","orcid":"https://orcid.org/0000-0003-1004-7753"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anyi Rao","raw_affiliation_strings":["Department of Computer Science, Stanford University, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669427","display_name":"Li\u2010Yi Wei","orcid":"https://orcid.org/0000-0002-1076-6339"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Yi Wei","raw_affiliation_strings":["Adobe Research, United States"],"affiliations":[{"raw_affiliation_string":"Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080348698","display_name":"Rubaiat Habib Kazi","orcid":"https://orcid.org/0009-0007-9781-0032"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rubaiat Habib Kazi","raw_affiliation_strings":["Adobe Research, United States"],"affiliations":[{"raw_affiliation_string":"Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037455703","display_name":"Hijung Valentina Shin","orcid":"https://orcid.org/0000-0001-8798-4580"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hijung Valentina Shin","raw_affiliation_strings":["Adobe Research, United States"],"affiliations":[{"raw_affiliation_string":"Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045835385","display_name":"Maneesh Agrawala","orcid":"https://orcid.org/0000-0002-8996-7327"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maneesh Agrawala","raw_affiliation_strings":["Department of Computer Science, Stanford University, United States and Roblox, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, United States and Roblox, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089941596"],"corresponding_institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.1727,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79324842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.998199999332428,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9878000020980835,"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/lyrics","display_name":"Lyrics","score":0.9364274740219116},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.8832248449325562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103599548339844},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6957358717918396},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.638953447341919},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5537993907928467},{"id":"https://openalex.org/keywords/harmony","display_name":"Harmony (color)","score":0.5151685476303101},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5055286884307861},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46696737408638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33675330877304077},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.16249406337738037},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.14153510332107544},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.06846511363983154}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9364274740219116},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.8832248449325562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103599548339844},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6957358717918396},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.638953447341919},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5537993907928467},{"id":"https://openalex.org/C2776453491","wikidata":"https://www.wikidata.org/wiki/Q5659234","display_name":"Harmony (color)","level":2,"score":0.5151685476303101},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5055286884307861},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46696737408638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33675330877304077},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.16249406337738037},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.14153510332107544},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.06846511363983154},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3586183.3606757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3586183.3606757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.14922","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14922","pdf_url":"https://arxiv.org/pdf/2308.14922","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":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-141787","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-141787","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.14922","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14922","pdf_url":"https://arxiv.org/pdf/2308.14922","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W228323234","https://openalex.org/W2029848040","https://openalex.org/W2053374418","https://openalex.org/W2081211779","https://openalex.org/W2090625014","https://openalex.org/W2117948609","https://openalex.org/W2120481501","https://openalex.org/W2191779130","https://openalex.org/W2333091651","https://openalex.org/W2414794891","https://openalex.org/W2525932717","https://openalex.org/W2611826103","https://openalex.org/W2891181371","https://openalex.org/W2963656477","https://openalex.org/W2983943451","https://openalex.org/W3009936995","https://openalex.org/W3015315843","https://openalex.org/W3031700288","https://openalex.org/W3034364644","https://openalex.org/W3099365940","https://openalex.org/W4214507171","https://openalex.org/W4214902115","https://openalex.org/W4234693825","https://openalex.org/W4250779854","https://openalex.org/W4283712710","https://openalex.org/W4312396403","https://openalex.org/W4312543717","https://openalex.org/W7043563363","https://openalex.org/W7071956723"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2999103397","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W2360952181","https://openalex.org/W4285478380","https://openalex.org/W2100255360","https://openalex.org/W2032810564"],"abstract_inverted_index":{"Musicians":[0],"and":[1,28,39,49,139],"fans":[2],"often":[3],"produce":[4],"lyric":[5,54,76,102,113,127],"videos,":[6,55],"a":[7,58,80,90,101,116],"form":[8],"of":[9,52,60,74,83,108,119,143],"music":[10,98],"videos":[11,24,114,128],"that":[12,94,126],"showcase":[13],"the":[14,31,43,72,75,106,141],"song\u2019s":[15],"lyrics,":[16],"for":[17],"their":[18],"favorite":[19],"songs.":[20],"However,":[21],"making":[22],"such":[23,67],"can":[25],"be":[26,35],"challenging":[27],"time-consuming":[29],"as":[30],"lyrics":[32],"need":[33],"to":[34,63],"added":[36],"in":[37,89,135],"synchrony":[38],"visual":[40],"harmony":[41],"with":[42],"video.":[44,103],"Informed":[45],"by":[46,111,130],"prior":[47],"work":[48],"close":[50],"examination":[51],"existing":[53],"we":[56],"propose":[57],"set":[59],"design":[61],"guidelines":[62,70,88],"help":[64],"creators":[65],"make":[66],"videos.":[68],"Our":[69],"ensure":[71],"readability":[73,138],"text":[77,137],"while":[78],"maintaining":[79,136],"unified":[81],"focus":[82,142],"attention.":[84,144],"We":[85,104],"instantiate":[86],"these":[87],"fully":[91],"automated":[92],"pipeline":[93,110,132],"converts":[95],"an":[96],"input":[97,120],"video":[99],"into":[100],"demonstrate":[105],"robustness":[107],"our":[109,131],"generating":[112],"from":[115],"diverse":[117],"range":[118],"sources.":[121],"A":[122],"user":[123],"study":[124],"shows":[125],"generated":[129],"are":[133],"effective":[134],"unifying":[140]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
