{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:43:32Z","timestamp":1778694212326,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888921","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance Estimation"],"prefix":"10.1109","author":[{"given":"Hengyi","family":"Hong","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoyu","family":"Wei","sequence":"additional","affiliation":[{"name":"IFlytek Research,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":"10.1109\/TASLP.2020.3047233"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053045"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746384"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096460"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715220"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3346297"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3382504"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448050"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01029"},{"key":"ref13","article-title":"The nerc-slip system for sound event localization and detection of DCASE2023 challenge","author":"Wang","year":"2023","journal-title":"DCASE2023 Challenge, Tech. Rep."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687782"},{"key":"ref15","article-title":"The distillation system for sound event localization and detection of DCASE2023 challenge","author":"Kang","year":"2023","journal-title":"DCASE2023 Challenge, Tech. Rep."},{"key":"ref16","article-title":"Data augmentation, neural networks, and ensemble methods for sound event localization and detection","author":"Kim","year":"2023","journal-title":"DCASE2023 Challenge, Tech. Rep."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094681"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref23","first-page":"72931","article-title":"STARSS23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume":"36","author":"Shimada","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Enhanced sound event localization and detection in real 360-degree audio-visual sound-scapes","author":"Roman","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446118"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.2635758"},{"key":"ref27","first-page":"165","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","volume-title":"DCASE Workshop","author":"Politis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref31","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":"DCASE2024 Challenge, Tech. Rep."},{"key":"ref32","article-title":"Leveraging reverberation and visual depth cues for sound event localization and detection with distance estimation","author":"Berghi","year":"2024","journal-title":"DCASE2024 Challenge, Tech. Rep."},{"key":"ref33","article-title":"Data augmentation and cross-fusion for audiovisual sound event localization and detection with source distance estimation","author":"Li","year":"2024","journal-title":"DCASE2024 Challenge, Tech. Rep."}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888921.pdf?arnumber=10888921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:11Z","timestamp":1774416131000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888921","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}