{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T20:00:56Z","timestamp":1784836856371,"version":"3.55.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2026.3712286","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:42:13Z","timestamp":1783712533000},"page":"2949-2953","source":"Crossref","is-referenced-by-count":0,"title":["General-Purpose Audio-Visual Sounding Object Localization Based on Semi-Automatic Annotation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6456-9928","authenticated-orcid":false,"given":"Shun","family":"Sakurai","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-0745","authenticated-orcid":false,"given":"Yoshiaki","family":"Bando","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0703-8293","authenticated-orcid":false,"given":"Keisuke","family":"Imoto","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4580-4868","authenticated-orcid":false,"given":"Masaki","family":"Onishi","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3589935"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886263"},{"key":"ref6","first-page":"3634","article-title":"AVR: Synergizing foundation models for audio-visual humor detection","volume-title":"Proc. Interspeech","author":"Sharma","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1983"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446516"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3586552"},{"key":"ref10","first-page":"140","article-title":"Stereo sound event localization and detection with onscreen\/offscreen classification","volume-title":"Proc. Workshop Detection Classification Acoust. Scenes Events Workshop","author":"Shimada","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3524120"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681586"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01265"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747644"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094781"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02194"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-709"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448050"},{"key":"ref26","first-page":"1","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref27","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747634"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref30","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32579"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref41","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref42","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP55912.2026.11461336"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11603380.pdf?arnumber=11603380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:02:50Z","timestamp":1784833370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11603380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/lsp.2026.3712286","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}