{"id":"https://openalex.org/W4387969711","doi":"https://doi.org/10.1145/3581783.3612592","title":"SEAR: Semantically-grounded Audio Representations","display_name":"SEAR: Semantically-grounded Audio Representations","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969711","doi":"https://doi.org/10.1145/3581783.3612592"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612592","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612592","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3581783.3612592","any_repository_has_fulltext":null},"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, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","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, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","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, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085315115"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14522692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2785","last_page":"2794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.992900013923645,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9779999852180481,"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":0.8037306070327759},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7296320796012878},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6840384006500244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5523515343666077},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4538600742816925},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4503346085548401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4436945915222168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3872661590576172},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3375794291496277},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.31717216968536377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037306070327759},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7296320796012878},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6840384006500244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5523515343666077},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4538600742816925},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4503346085548401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4436945915222168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3872661590576172},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3375794291496277},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.31717216968536377},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612592","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612592","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612592","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612592","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2044807399","https://openalex.org/W2052666245","https://openalex.org/W2055251102","https://openalex.org/W2142194269","https://openalex.org/W2593116425","https://openalex.org/W2618799552","https://openalex.org/W2619697695","https://openalex.org/W2889089254","https://openalex.org/W2936299888","https://openalex.org/W2962711930","https://openalex.org/W2962865004","https://openalex.org/W2981851019","https://openalex.org/W3015591594","https://openalex.org/W3034364644","https://openalex.org/W3110420575","https://openalex.org/W3119957342","https://openalex.org/W3162391496","https://openalex.org/W3174906557","https://openalex.org/W3175300676","https://openalex.org/W3176445421","https://openalex.org/W3201143670","https://openalex.org/W3209059054","https://openalex.org/W3216765867","https://openalex.org/W4205689591","https://openalex.org/W4284898017","https://openalex.org/W4319300292","https://openalex.org/W6600704668","https://openalex.org/W6601211009","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Audio":[0],"supports":[1],"visual":[2,19,59,80],"story-telling":[3],"in":[4,66,140,146],"movies":[5],"through":[6,144],"the":[7,24,50,85,103,106,134],"use":[8],"of":[9,39,47,87,98,105],"different":[10,18],"sounds.":[11],"These":[12],"sounds":[13],"are":[14],"often":[15],"tied":[16],"to":[17,61,75,84,90],"elements,":[20],"including":[21],"foreground":[22],"entities,":[23],"interactions":[25],"between":[26,52],"them":[27],"as":[28,30],"well":[29],"background":[31],"context.":[32],"Visual":[33],"captions":[34,60,81,89],"provide":[35],"a":[36,43,67,141],"condensed":[37],"view":[38],"an":[40],"image,":[41],"providing":[42],"natural":[44],"language":[45],"description":[46],"entities":[48],"and":[49,109,120,127,151],"relationships":[51],"them.":[53],"In":[54],"this":[55],"work,":[56],"we":[57,131],"utilize":[58],"semantically":[62],"ground":[63],"audio":[64,92,128],"representations":[65,93,108],"self-supervised":[68],"setup.":[69],"We":[70,101],"leverage":[71],"state-of-the-art":[72],"vision-language":[73],"models":[74],"augment":[76],"movie":[77,99,116,148],"datasets":[78],"with":[79],"at":[82],"scale":[83],"order":[86],"9.6M":[88],"learn":[91],"from":[94],"over":[95],"2500":[96],"hours":[97],"data.":[100],"evaluate":[102],"utility":[104],"learned":[107,135],"show":[110,132],"state-of-the":[111],"art":[112],"performance":[113],"on":[114],"two":[115],"understanding":[117,149],"tasks,":[118],"genre":[119],"speaking-style":[121],"classification,":[122],"outperforming":[123],"video":[124],"based":[125],"methods":[126],"baselines.":[129],"Finally,":[130],"that":[133],"model":[136],"can":[137],"be":[138],"transferred":[139],"zero-shot":[142],"manner":[143],"application":[145],"both":[147],"tasks":[150],"general":[152],"action":[153],"recognition.":[154]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}