{"id":"https://openalex.org/W2964011431","doi":"https://doi.org/10.1109/tmm.2018.2871418","title":"Weakly-Supervised Visual Instrument-Playing Action Detection in Videos","display_name":"Weakly-Supervised Visual Instrument-Playing Action Detection in Videos","publication_year":2018,"publication_date":"2018-09-20","ids":{"openalex":"https://openalex.org/W2964011431","doi":"https://doi.org/10.1109/tmm.2018.2871418","mag":"2964011431"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2018.2871418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2018.2871418","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5101719938","display_name":"Jen-Yu Liu","orcid":"https://orcid.org/0000-0003-1299-6688"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Yu Liu","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-1299-6688","affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"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":["CITI, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CITI, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028285867","display_name":"Shyh\u2010Kang Jeng","orcid":"https://orcid.org/0000-0001-8960-9995"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shyh-Kang Jeng","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-8960-9995","affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8043,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.86731544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"21","issue":"4","first_page":"887","last_page":"901"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9941999912261963,"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":0.870761513710022},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6308757066726685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987977385520935},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5545300841331482},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41034454107284546},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33744508028030396},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33553409576416016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.870761513710022},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6308757066726685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987977385520935},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5545300841331482},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41034454107284546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33744508028030396},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33553409576416016},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2018.2871418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2018.2871418","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W122025198","https://openalex.org/W639708223","https://openalex.org/W753847829","https://openalex.org/W797104241","https://openalex.org/W1483393862","https://openalex.org/W1526676615","https://openalex.org/W1536680647","https://openalex.org/W1755205674","https://openalex.org/W1836465849","https://openalex.org/W1903029394","https://openalex.org/W1923404803","https://openalex.org/W1973054923","https://openalex.org/W1994488211","https://openalex.org/W1999536323","https://openalex.org/W2005562282","https://openalex.org/W2023619251","https://openalex.org/W2029859592","https://openalex.org/W2107430826","https://openalex.org/W2108710284","https://openalex.org/W2112796928","https://openalex.org/W2114708606","https://openalex.org/W2117539524","https://openalex.org/W2119821739","https://openalex.org/W2127615536","https://openalex.org/W2127870748","https://openalex.org/W2146502635","https://openalex.org/W2156303437","https://openalex.org/W2163605009","https://openalex.org/W2210641851","https://openalex.org/W2296724634","https://openalex.org/W2342662179","https://openalex.org/W2354870669","https://openalex.org/W2410860376","https://openalex.org/W2422581341","https://openalex.org/W2477205648","https://openalex.org/W2519750370","https://openalex.org/W2524365899","https://openalex.org/W2525577390","https://openalex.org/W2535046761","https://openalex.org/W2575145750","https://openalex.org/W2590294899","https://openalex.org/W2593116425","https://openalex.org/W2618530766","https://openalex.org/W2619329613","https://openalex.org/W2623327532","https://openalex.org/W2623350015","https://openalex.org/W2651884604","https://openalex.org/W2962756039","https://openalex.org/W2963173190","https://openalex.org/W2964214371","https://openalex.org/W3098670224","https://openalex.org/W3101203783","https://openalex.org/W3103314642","https://openalex.org/W3108131700","https://openalex.org/W3210141620","https://openalex.org/W4239510810","https://openalex.org/W4293665662","https://openalex.org/W4294576248","https://openalex.org/W4301188081","https://openalex.org/W6620707391","https://openalex.org/W6638667902","https://openalex.org/W6640257725","https://openalex.org/W6648737282","https://openalex.org/W6678969435","https://openalex.org/W6681435938","https://openalex.org/W6682864246","https://openalex.org/W6696126599","https://openalex.org/W6697040288","https://openalex.org/W6729831399","https://openalex.org/W6738806211","https://openalex.org/W6738813860"],"related_works":["https://openalex.org/W2737719445","https://openalex.org/W2961085424","https://openalex.org/W2898210368","https://openalex.org/W2382480268","https://openalex.org/W2755342338","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W2775347418","https://openalex.org/W2604548540"],"abstract_inverted_index":{"Music":[0],"videos":[1],"are":[2,42,46,115,187],"one":[3],"of":[4,9,60,69,80,91,176,203,216],"the":[5,18,29,33,50,55,66,77,81,85,92,113,118,140,151,173,192,201,204],"most":[6,19],"popular":[7],"types":[8],"video":[10,179],"streaming":[11],"services,":[12],"and":[13,48,111,130,163,184,208],"instrument":[14,71],"playing":[15,51,72],"is":[16,36,84],"among":[17],"common":[20],"scenes":[21,31],"in":[22,32,54,76,87,117],"such":[23],"videos.":[24,119],"In":[25],"order":[26],"to":[27,38,108,135,171,180],"understand":[28],"instrument-playing":[30,141],"videos,":[34],"it":[35],"important":[37],"know":[39],"what":[40],"instruments":[41,61,114,186],"played,":[43,47],"when":[44,110],"they":[45],"where":[49,112,185],"actions":[52],"occur":[53],"scene.":[56],"While":[57],"audio-based":[58],"recognition":[59],"has":[62],"been":[63],"widely":[64],"studied,":[65],"visual":[67,174],"aspect":[68],"music":[70,178],"remains":[73],"largely":[74],"unaddressed":[75],"literature.":[78],"One":[79],"main":[82],"obstacles":[83],"difficulty":[86],"collecting":[88],"annotated":[89],"data":[90],"action":[93,142],"locations":[94],"for":[95,138],"training-based":[96],"methods.":[97],"To":[98],"address":[99],"this":[100],"issue,":[101],"we":[102,220],"propose":[103,121],"a":[104,127,177,211],"weakly":[105],"supervised":[106],"framework":[107],"find":[109],"played":[116],"We":[120,189,199],"using":[122],"two":[123],"auxiliary":[124],"models:":[125],"1)":[126],"sound":[128,145],"model":[129,134,146,153,168],"2)":[131],"an":[132],"object":[133,152],"provide":[136,161],"supervision":[137],"training":[139],"model.":[143],"The":[144,166],"provides":[147,154],"temporal":[148,162],"supervisions,":[149],"while":[150],"spatial":[155,164],"supervisions.":[156,165],"They":[157],"together":[158],"can":[159],"simultaneously":[160],"resulting":[167],"only":[169],"needs":[170],"analyze":[172],"part":[175],"deduce":[181],"which,":[182],"when,":[183],"played.":[188],"found":[190],"that":[191,219],"proposed":[193,205],"method":[194,206],"significantly":[195],"improves":[196],"localization":[197],"accuracy.":[198],"evaluate":[200],"result":[202],"temporally":[207],"spatially":[209],"on":[210],"small":[212],"dataset":[213],"(a":[214],"total":[215],"5400":[217],"frames)":[218],"manually":[221],"annotated.":[222]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
