{"id":"https://openalex.org/W4405785001","doi":"https://doi.org/10.1109/iros58592.2024.10802318","title":"Visual Timing For Sound Source Depth Estimation in the Wild","display_name":"Visual Timing For Sound Source Depth Estimation in the Wild","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785001","doi":"https://doi.org/10.1109/iros58592.2024.10802318"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5046339814","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0002-3424-9643"},"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":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":["The University of Texas at Austin,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032760128","display_name":"Lili Qiu","orcid":"https://orcid.org/0000-0002-1590-9749"},"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":false,"raw_author_name":"Lili Qiu","raw_affiliation_strings":["The University of Texas at Austin,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12348","last_page":"12355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9915000200271606,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9915000200271606,"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/T11309","display_name":"Music and Audio Processing","score":0.987500011920929,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5996724367141724},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5919556617736816},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.504852831363678},{"id":"https://openalex.org/keywords/auditory-display","display_name":"Auditory display","score":0.4171293377876282},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.37196680903434753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3401715159416199},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33578482270240784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3225201666355133},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3195933997631073},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10917547345161438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996724367141724},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5919556617736816},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.504852831363678},{"id":"https://openalex.org/C171179263","wikidata":"https://www.wikidata.org/wiki/Q4820026","display_name":"Auditory display","level":2,"score":0.4171293377876282},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.37196680903434753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3401715159416199},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33578482270240784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3225201666355133},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3195933997631073},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10917547345161438},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W2056898157","https://openalex.org/W2104422351","https://openalex.org/W2115579991","https://openalex.org/W2194775991","https://openalex.org/W2594690981","https://openalex.org/W2931433835","https://openalex.org/W2944745281","https://openalex.org/W2963115079","https://openalex.org/W2963483509","https://openalex.org/W2963867516","https://openalex.org/W2964109005","https://openalex.org/W2964251418","https://openalex.org/W2966356884","https://openalex.org/W2972541922","https://openalex.org/W2979507566","https://openalex.org/W2989833651","https://openalex.org/W2990113535","https://openalex.org/W3034653753","https://openalex.org/W3081218555","https://openalex.org/W3090139470","https://openalex.org/W3108655859","https://openalex.org/W3109908659","https://openalex.org/W3139813613","https://openalex.org/W3168472259","https://openalex.org/W3174856432","https://openalex.org/W3175720495","https://openalex.org/W4214635352","https://openalex.org/W4312415534","https://openalex.org/W4312823237","https://openalex.org/W4313072308","https://openalex.org/W4372348432","https://openalex.org/W4403759581"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W2037001540","https://openalex.org/W4313595395","https://openalex.org/W2312783472"],"abstract_inverted_index":{"Depth":[0],"estimation":[1,74,97],"enables":[2],"a":[3,40,114,157,179],"wide":[4],"variety":[5],"of":[6,86],"3D":[7],"applications,":[8],"such":[9],"as":[10,98],"robotics":[11],"and":[12,89,131,146,185],"autonomous":[13],"driving.":[14],"Despite":[15],"significant":[16],"work":[17],"on":[18,79],"various":[19],"depth":[20,56,73,96,110],"sensors,":[21],"it":[22],"is":[23,77],"challenging":[24],"to":[25,30,53,117,125,150,160,171,183],"develop":[26,67],"an":[27,99],"all-in-one":[28],"method":[29],"meet":[31],"multiple":[32],"basic":[33],"criteria.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,66,112],"propose":[39],"novel":[41],"audio-visual":[42,72,100,129],"learning":[43],"scheme":[44],"by":[45,62,127],"integrating":[46],"semantic":[47],"features":[48,149],"with":[49,57,142,165],"physical":[50],"spatial":[51],"cues":[52],"boost":[54],"monocular":[55,184],"only":[58],"one":[59],"microphone.":[60],"Inspired":[61],"the":[63,69,80,83,87,90,119,137,143,152],"flash-to-bang":[64],"theory,":[65],"FBDepth,":[68],"first":[70],"passive":[71],"framework.":[75],"It":[76],"based":[78],"difference":[81],"between":[82],"time-of-flight":[84],"(ToF)":[85],"light":[88],"sound.":[91],"We":[92,155],"formulate":[93],"sound":[94],"source":[95,153],"event":[101],"localization":[102,121],"task":[103],"for":[104],"collision":[105],"events.":[106],"To":[107],"approach":[108],"decimeter-level":[109],"accuracy,":[111],"design":[113],"coarse-to-fine":[115],"pipeline":[116],"push":[118],"temporary":[120],"accuracy":[122],"from":[123],"event-level":[124],"millisecond-level":[126],"aligning":[128],"correspondence":[130],"manipulating":[132],"optical":[133],"flow.":[134],"FBDepth":[135,173],"feeds":[136],"estimated":[138],"visual":[139,148],"timestamp":[140],"together":[141],"audio":[144],"clip":[145],"objects":[147,168],"regress":[151],"depth.":[154],"use":[156],"mobile":[158],"phone":[159],"collect":[161],"3.6K+":[162],"video":[163],"clips":[164],"24":[166],"different":[167],"at":[169,178],"up":[170],"65m.":[172],"shows":[174],"superior":[175],"performance":[176],"especially":[177],"long":[180],"range":[181],"compared":[182],"stereo":[186],"methods.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}