{"id":"https://openalex.org/W4381333750","doi":"https://doi.org/10.1007/s11263-023-01816-8","title":"Visually-Guided Audio Spatialization in Video with Geometry-Aware Multi-task Learning","display_name":"Visually-Guided Audio Spatialization in Video with Geometry-Aware Multi-task Learning","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4381333750","doi":"https://doi.org/10.1007/s11263-023-01816-8"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-023-01816-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-023-01816-8","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","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/A5100720830","display_name":"Rishabh Garg","orcid":"https://orcid.org/0000-0003-4224-4890"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rishabh Garg","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4224-4890","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907601","display_name":"Ruohan Gao","orcid":"https://orcid.org/0000-0002-8346-1114"},"institutions":[{"id":"https://openalex.org/I1743320","display_name":"Palo Alto University","ror":"https://ror.org/04f812k67","country_code":"US","type":"education","lineage":["https://openalex.org/I1743320"]},{"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":"Ruohan Gao","raw_affiliation_strings":["Stanford University, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1743320","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012765543","display_name":"Kristen Grauman","orcid":"https://orcid.org/0000-0002-9591-5873"},"institutions":[{"id":"https://openalex.org/I4210140397","display_name":"Metrica (United States)","ror":"https://ror.org/031ffw737","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140397"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Grauman","raw_affiliation_strings":["FAIR, Meta AI, Austin, TX, USA","The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta AI, Austin, TX, USA","institution_ids":["https://openalex.org/I4210140397"]},{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100720830"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":null,"fwci":1.8974,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86484477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"131","issue":"10","first_page":"2723","last_page":"2737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9950000047683716,"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/binaural-recording","display_name":"Binaural recording","score":0.9295274019241333},{"id":"https://openalex.org/keywords/spatialization","display_name":"Spatialization","score":0.8342315554618835},{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.8317103385925293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7904238700866699},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6003748178482056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4870913028717041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4855923056602478},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43020206689834595},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.42321962118148804},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.4216269552707672},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4208527207374573},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.41486459970474243},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.25291380286216736},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18107914924621582},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08830264210700989}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.9295274019241333},{"id":"https://openalex.org/C2777031145","wikidata":"https://www.wikidata.org/wiki/Q4430987","display_name":"Spatialization","level":2,"score":0.8342315554618835},{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.8317103385925293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904238700866699},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6003748178482056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4870913028717041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4855923056602478},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43020206689834595},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.42321962118148804},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.4216269552707672},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4208527207374573},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41486459970474243},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.25291380286216736},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18107914924621582},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08830264210700989},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-023-01816-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-023-01816-8","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1557831657","https://openalex.org/W1901129140","https://openalex.org/W2033875152","https://openalex.org/W2120847449","https://openalex.org/W2152859600","https://openalex.org/W2194775991","https://openalex.org/W2318686747","https://openalex.org/W2474638510","https://openalex.org/W2511428026","https://openalex.org/W2551572271","https://openalex.org/W2586821239","https://openalex.org/W2619697695","https://openalex.org/W2809642605","https://openalex.org/W2809716557","https://openalex.org/W2962699416","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963082324","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963290645","https://openalex.org/W2963680395","https://openalex.org/W2963807156","https://openalex.org/W2964109005","https://openalex.org/W2964339842","https://openalex.org/W2964345931","https://openalex.org/W2970906079","https://openalex.org/W2970971581","https://openalex.org/W2972513594","https://openalex.org/W2981816492","https://openalex.org/W2981851635","https://openalex.org/W2982624843","https://openalex.org/W2986479369","https://openalex.org/W2988200020","https://openalex.org/W2990113535","https://openalex.org/W3009928773","https://openalex.org/W3015383493","https://openalex.org/W3017343282","https://openalex.org/W3034658206","https://openalex.org/W3034742263","https://openalex.org/W3041795964","https://openalex.org/W3046890131","https://openalex.org/W3089887959","https://openalex.org/W3089944088","https://openalex.org/W3092603041","https://openalex.org/W3095687795","https://openalex.org/W3096431533","https://openalex.org/W3096780661","https://openalex.org/W3108240585","https://openalex.org/W3108332675","https://openalex.org/W3108655859","https://openalex.org/W3118120400","https://openalex.org/W3174854700","https://openalex.org/W3176232375","https://openalex.org/W3182657421","https://openalex.org/W3196679123","https://openalex.org/W4214681287","https://openalex.org/W4214759869","https://openalex.org/W4251733995","https://openalex.org/W4289665794","https://openalex.org/W4312498304","https://openalex.org/W4312779270","https://openalex.org/W6631190155","https://openalex.org/W6758675244","https://openalex.org/W6792340124"],"related_works":["https://openalex.org/W2072124114","https://openalex.org/W3112787525","https://openalex.org/W2072738923","https://openalex.org/W3167845207","https://openalex.org/W3084062281","https://openalex.org/W4389394004","https://openalex.org/W1991590679","https://openalex.org/W2162261685","https://openalex.org/W2056551376","https://openalex.org/W2024318353"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
