{"id":"https://openalex.org/W4375869234","doi":"https://doi.org/10.1109/icassp49357.2023.10094781","title":"A Dataset for Audio-Visual Sound Event Detection in Movies","display_name":"A Dataset for Audio-Visual Sound Event Detection in Movies","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869234","doi":"https://doi.org/10.1109/icassp49357.2023.10094781"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5085315115","display_name":"Rajat Hebbar","orcid":"https://orcid.org/0000-0002-0904-0573"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rajat Hebbar","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory","Signal Analysis and Interpretation Laboratory, University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059652479","display_name":"Digbalay Bose","orcid":"https://orcid.org/0000-0002-5281-1695"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Digbalay Bose","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory","Signal Analysis and Interpretation Laboratory, University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory","Signal Analysis and Interpretation Laboratory, University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020900185","display_name":"Veena Vijai","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Veena Vijai","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory","Signal Analysis and Interpretation Laboratory, University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory","Signal Analysis and Interpretation Laboratory, University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085315115"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.834,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85896714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9894999861717224,"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":0.9656999707221985,"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":0.8104737997055054},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6852418780326843},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.584343671798706},{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.5599372982978821},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4590228497982025},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4471049904823303},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4314590394496918},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42406606674194336},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3900412619113922},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3845444321632385},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33680254220962524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29664650559425354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104737997055054},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6852418780326843},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.584343671798706},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.5599372982978821},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4590228497982025},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4471049904823303},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4314590394496918},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42406606674194336},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3900412619113922},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3845444321632385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33680254220962524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29664650559425354},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":46,"referenced_works":["https://openalex.org/W118681204","https://openalex.org/W821549425","https://openalex.org/W1996473935","https://openalex.org/W2038484192","https://openalex.org/W2133948225","https://openalex.org/W2147917435","https://openalex.org/W2511089602","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2768188490","https://openalex.org/W2770119437","https://openalex.org/W2775505379","https://openalex.org/W2889089254","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2959539607","https://openalex.org/W2970641574","https://openalex.org/W2972119347","https://openalex.org/W2990113535","https://openalex.org/W2990396912","https://openalex.org/W2997909293","https://openalex.org/W3015371781","https://openalex.org/W3035323656","https://openalex.org/W3035333188","https://openalex.org/W3093096945","https://openalex.org/W3094550259","https://openalex.org/W3120041065","https://openalex.org/W3142611481","https://openalex.org/W3154596443","https://openalex.org/W3166396011","https://openalex.org/W3170874841","https://openalex.org/W3174906557","https://openalex.org/W3196974791","https://openalex.org/W4205689591","https://openalex.org/W4385245566","https://openalex.org/W6604849252","https://openalex.org/W6739901393","https://openalex.org/W6745930336","https://openalex.org/W6746278845","https://openalex.org/W6747331233","https://openalex.org/W6755207826","https://openalex.org/W6767908396","https://openalex.org/W6788135285","https://openalex.org/W6791353385","https://openalex.org/W6793736971","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2384738070","https://openalex.org/W2065633372","https://openalex.org/W2328398924","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W1590604789","https://openalex.org/W2792033502","https://openalex.org/W3043119899","https://openalex.org/W4254486954"],"abstract_inverted_index":{"Audio":[0],"event":[1],"detection":[2],"is":[3,37],"a":[4,53,58,69,113,141],"widely":[5],"studied":[6],"field,":[7],"with":[8],"applications":[9],"ranging":[10],"from":[11,92],"self-driving":[12],"cars":[13],"to":[14,39,85,99,111],"healthcare.":[15],"In-the-wild":[16],"datasets":[17],"such":[18],"as":[19],"Audioset":[20],"have":[21],"propelled":[22],"research":[23,173],"in":[24,124,136],"this":[25,65],"field.":[26],"However,":[27],"many":[28],"efforts":[29],"typically":[30],"involve":[31],"manual":[32],"annotation":[33],"and":[34,47,106,128,153,167],"verification,":[35],"which":[36,50],"expensive":[38],"perform":[40],"at":[41,174],"scale.":[42],"Movies":[43],"depict":[44],"various":[45],"real-life":[46],"fictional":[48],"scenarios":[49],"makes":[51],"them":[52],"rich":[54],"resource":[55],"for":[56,144,172],"mining":[57],"wide":[59],"range":[60],"of":[61,71,116,134,148],"audio":[62,72,90,101],"events.":[63],"In":[64],"work,":[66],"we":[67],"present":[68,107],"dataset":[70],"events":[73,91],"called":[74],"Subtitle-Aligned":[75],"Movie":[76],"Sounds":[77],"(SAM-S).":[78],"We":[79,95,119,139],"use":[80],"publicly":[81],"available":[82,171],"closed-caption":[83],"transcripts":[84],"automatically":[86],"mine":[87],"over":[88],"110K":[89],"430":[93],"movies.":[94],"identify":[96],"three":[97],"dimensions":[98],"categorize":[100],"events:":[102],"sound,":[103],"source,":[104],"quality,":[105],"the":[108,121,126,131,162],"steps":[109],"involved":[110,123],"produce":[112],"final":[114],"taxonomy":[115],"245":[117],"sounds.":[118],"discuss":[120],"choices":[122],"generating":[125],"taxonomy,":[127],"also":[129],"highlight":[130],"human-centered":[132],"nature":[133],"sounds":[135],"our":[137],"dataset.":[138],"establish":[140],"baseline":[142],"performance":[143,163],"audio-only":[145],"sound":[146],"classification":[147],"34.76%":[149],"mean":[150],"average":[151],"precision,":[152],"show":[154],"that":[155],"incorporating":[156],"visual":[157],"information":[158],"can":[159],"further":[160],"improve":[161],"by":[164],"5%.":[165],"Data":[166],"code":[168],"are":[169],"made":[170],"https://github.com/usc-sail/mica-subtitle-aligned-movie-sounds":[175]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}