{"id":"https://openalex.org/W4392902762","doi":"https://doi.org/10.1109/icassp48485.2024.10447683","title":"Self-Motion As Supervision For Egocentric Audiovisual Localization","display_name":"Self-Motion As Supervision For Egocentric Audiovisual Localization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902762","doi":"https://doi.org/10.1109/icassp48485.2024.10447683"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071106886","display_name":"Calvin Murdock","orcid":"https://orcid.org/0000-0002-9560-4506"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvin Murdock","raw_affiliation_strings":["Reality Labs Research at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research at Meta","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037474835","display_name":"Ishwarya Ananthabhotla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ishwarya Ananthabhotla","raw_affiliation_strings":["Reality Labs Research at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research at Meta","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101983122","display_name":"Hao L\u00fc","orcid":"https://orcid.org/0000-0001-6887-1767"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Lu","raw_affiliation_strings":["Reality Labs Research at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research at Meta","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108520440","display_name":"Vamsi Krishna Ithapu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamsi Krishna Ithapu","raw_affiliation_strings":["Reality Labs Research at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research at Meta","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210128585"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7835","last_page":"7839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11448","display_name":"Face recognition and analysis","score":0.9959999918937683,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.7772644758224487},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.7432016730308533},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6367284059524536},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5680440068244934},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5221574306488037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5212115049362183},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5169388651847839},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.43196630477905273},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4216683506965637},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3983500003814697},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38277438282966614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772644758224487},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7432016730308533},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6367284059524536},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5680440068244934},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5221574306488037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5212115049362183},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5169388651847839},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.43196630477905273},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4216683506965637},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3983500003814697},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38277438282966614},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1548471706","https://openalex.org/W2001183000","https://openalex.org/W2070099923","https://openalex.org/W2136668269","https://openalex.org/W2150839178","https://openalex.org/W2558906385","https://openalex.org/W2741156154","https://openalex.org/W2795307598","https://openalex.org/W2962960500","https://openalex.org/W2963680395","https://openalex.org/W2971852403","https://openalex.org/W3016098309","https://openalex.org/W3034742263","https://openalex.org/W3101840568","https://openalex.org/W3172472082","https://openalex.org/W3177116139","https://openalex.org/W3179026300","https://openalex.org/W3183863723","https://openalex.org/W3185121129","https://openalex.org/W3205786327","https://openalex.org/W3206008172","https://openalex.org/W4225096074","https://openalex.org/W4306706366","https://openalex.org/W4312268709","https://openalex.org/W4312356258","https://openalex.org/W4312466984","https://openalex.org/W4386057737","https://openalex.org/W6797761920","https://openalex.org/W6846145006"],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W3014378845","https://openalex.org/W4240909707","https://openalex.org/W2059546927","https://openalex.org/W3207760378","https://openalex.org/W4386072035","https://openalex.org/W2562758970","https://openalex.org/W1986970529","https://openalex.org/W1563178652","https://openalex.org/W2947492009"],"abstract_inverted_index":{"Sound":[0],"source":[1],"localization":[2,94,121],"is":[3,39],"a":[4,114],"key":[5],"requirement":[6],"for":[7,116],"many":[8],"assistive":[9],"applications":[10],"of":[11,23,77,83,91],"augmented":[12],"reality,":[13],"such":[14,62],"as":[15,63,113],"speech":[16],"enhancement.":[17],"In":[18,80],"conversational":[19],"settings,":[20],"potential":[21],"sources":[22],"interest":[24],"may":[25],"be":[26],"approximated":[27],"by":[28],"active":[29,119],"speaker":[30,120],"detection.":[31],"However,":[32],"localizing":[33],"speakers":[34],"in":[35,55],"crowded,":[36],"noisy":[37],"environments":[38],"challenging,":[40],"particularly":[41],"without":[42],"extensive":[43],"ground":[44,84],"truth":[45,85],"annotations.":[46],"Still,":[47],"people":[48],"are":[49],"often":[50],"able":[51],"to":[52,73,98],"communicate":[53],"effectively":[54],"these":[56],"scenarios":[57],"through":[58],"orienting":[59],"behavioral":[60,96],"responses,":[61],"head":[64,127],"motion":[65],"and":[66,122,128],"eye":[67],"gaze,":[68],"which":[69],"have":[70],"been":[71],"shown":[72],"correlate":[74],"with":[75,95,102],"directions":[76,130],"auditory":[78],"sources.":[79],"the":[81],"absence":[82],"annotations,":[86],"we":[87],"propose":[88],"joint":[89],"training":[90],"egocentric":[92,118],"audiovisual":[93,100],"pseudolabels":[97,124],"relate":[99],"stimuli":[101],"directional":[103],"information":[104],"extracted":[105],"from":[106,126],"future":[107],"behavior.":[108],"We":[109],"evaluate":[110],"this":[111],"method":[112],"technique":[115],"unsupervised":[117],"compare":[123],"derived":[125],"gaze":[129],"against":[131],"fully-supervised":[132],"alternatives.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}