{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:26Z","timestamp":1761894686963,"version":"build-2065373602"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210146","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Incorporating Audio-Guided Visual Attention into Sound Event Localization and Detection with Source Distance Estimation"],"prefix":"10.1109","author":[{"given":"Qing","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengyi","family":"Hong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maocheng","family":"Hu","sequence":"additional","affiliation":[{"name":"National Intelligent Voice Innovation Center,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingqi","family":"Cai","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Fang","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref2","first-page":"11","article-title":"Event-independent network for polyphonic sound event localization and detection","author":"Cao","year":"2020","journal-title":"DCASE Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3173054"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3284525"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746384"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096460"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447181"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-145"},{"article-title":"SELD-Mamba: Selective state-space model for sound event localization and detection with source distance estimation","year":"2024","author":"Mu","key":"ref12"},{"key":"ref13","first-page":"72931","article-title":"STARSS23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","author":"Shimada","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715220"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3226330"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","article-title":"The distillation system for sound event localization and detection of DCASE2023 challenge","author":"Kang","year":"2023","journal-title":"Tech. Rep., DCASE2023 Challenge"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448050"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687782"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888921"},{"article-title":"Few-shot sound source distance estimation using relation networks","year":"2021","author":"Sobhdel","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3382504"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3346297"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref25","article-title":"The NERC-SLIP system for sound event localization and detection with source distance estimation of DCASE 2024 challenge","author":"Wang","year":"2024","journal-title":"Tech. Rep., DCASE2024 Challenge"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094681"},{"key":"ref28","article-title":"Audio vision: Using audio-visual synchrony to locate sounds","volume":"12","author":"Hershey","year":"1999","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446118"},{"article-title":"Enhanced sound event localization and detection in real 360-degree audio-visual soundscapes","year":"2024","author":"Roman","key":"ref31"},{"article-title":"METU SPARG eigenmike em32 acoustic impulse response dataset v0. 1.0","year":"2019","author":"Olgun","key":"ref32"},{"key":"ref33","first-page":"165","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"Politis","year":"2020","journal-title":"DCASE Workshop"},{"key":"ref34","article-title":"Leveraging reverberation and visual depth cues for sound event localization and detection with distance estimation","author":"Berghi","year":"2024","journal-title":"Tech. Rep., DCASE2024 Challenge"},{"key":"ref35","article-title":"Data augmentation and cross-fusion for audiovisual sound event localization and detection with source distance estimation","author":"Li","year":"2024","journal-title":"Tech. Rep., DCASE2024 Challenge"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210146.pdf?arnumber=11210146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:32Z","timestamp":1761888812000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210146","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}