{"id":"https://openalex.org/W4416059769","doi":"https://doi.org/10.1109/iccv51701.2025.01869","title":"What's Making That Sound Right Now? Video-Centric Audio-Visual Localization","display_name":"What's Making That Sound Right Now? Video-Centric Audio-Visual Localization","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416059769","doi":"https://doi.org/10.1109/iccv51701.2025.01869"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.04667","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hahyeon Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hahyeon Choi","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036313703","display_name":"J.P. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junhoo Lee","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084897975","display_name":"Nojun Kwak","orcid":"https://orcid.org/0000-0002-1792-0327"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nojun Kwak","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20095","last_page":"20104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9032999873161316,"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":0.9032999873161316,"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":0.061000000685453415,"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":0.008500000461935997,"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/focus","display_name":"Focus (optics)","score":0.6819000244140625},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.572700023651123},{"id":"https://openalex.org/keywords/temporal-resolution","display_name":"Temporal resolution","score":0.4212000072002411},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.37040001153945923},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.36309999227523804},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3402000069618225},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32019999623298645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283999919891357},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6819000244140625},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44999998807907104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.37040001153945923},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.04667","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04667","pdf_url":"https://arxiv.org/pdf/2507.04667","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.04667","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.04667","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.04667","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04667","pdf_url":"https://arxiv.org/pdf/2507.04667","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1185891446","display_name":null,"funder_award_id":"2021R1A2C3006659","funder_id":"https://openalex.org/F4320309788","funder_display_name":"Neurosciences Research Foundation"},{"id":"https://openalex.org/G276880814","display_name":null,"funder_award_id":"RS-2021-II211343, RS-2022-II220320","funder_id":"https://openalex.org/F4320319144","funder_display_name":"Indian Institute of Technology, Patna"}],"funders":[{"id":"https://openalex.org/F4320309788","display_name":"Neurosciences Research Foundation","ror":"https://ror.org/05exfab56"},{"id":"https://openalex.org/F4320319144","display_name":"Indian Institute of Technology, Patna","ror":"https://ror.org/01ft5vz71"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio-Visual":[0],"Localization":[1],"(AVL)":[2],"aims":[3],"to":[4,21,99,104],"identify":[5],"sound-emitting":[6],"sources":[7,32],"within":[8],"a":[9,39,49,71,82,141],"visual":[10],"scene.":[11],"However,":[12],"existing":[13],"studies":[14],"focus":[15],"on":[16,107],"image-level":[17],"audio-visual":[18,121,146],"associations,":[19],"failing":[20],"capture":[22],"temporal":[23,56,90,101,126,135],"dynamics.":[24],"Moreover,":[25],"they":[26],"assume":[27],"simplified":[28],"scenarios":[29,62],"where":[30],"sound":[31],"are":[33],"always":[34],"visible":[35],"and":[36,67,111,119,139],"involve":[37],"only":[38],"single":[40],"object.":[41],"To":[42],"address":[43],"these":[44],"limitations,":[45],"we":[46,79],"propose":[47],"AVATAR,":[48],"video-centric":[50,84,145],"AVL":[51,76,85,138],"benchmark":[52],"that":[53,87,95],"incorporates":[54],"high-resolution":[55,125],"information.":[57,91],"AVATAR":[58],"introduces":[59],"four":[60],"distinct":[61],"--":[63,69],"Single-sound,":[64],"Mixed-sound,":[65],"Multi-entity,":[66],"Off-screen":[68],"enabling":[70],"more":[72],"comprehensive":[73],"evaluation":[74],"of":[75,134],"models.":[77],"Additionally,":[78],"present":[80],"TAVLO,":[81],"novel":[83],"model":[86],"explicitly":[88],"integrates":[89],"Experimental":[92],"results":[93],"show":[94],"conventional":[96],"methods":[97],"struggle":[98],"track":[100],"variations":[102],"due":[103],"their":[105],"reliance":[106],"global":[108],"audio":[109],"features":[110],"frame-level":[112],"mappings.":[113],"In":[114],"contrast,":[115],"TAVLO":[116],"achieves":[117],"robust":[118],"precise":[120],"alignment":[122],"by":[123],"leveraging":[124],"modeling.":[127],"Our":[128],"work":[129],"empirically":[130],"demonstrates":[131],"the":[132],"importance":[133],"dynamics":[136],"in":[137],"establishes":[140],"new":[142],"standard":[143],"for":[144],"localization.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}