{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:52:57Z","timestamp":1776181977834,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687782","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["Exploring Audio-Visual Information Fusion for Sound Event Localization and Detection In Low-Resource Realistic Scenarios"],"prefix":"10.1109","author":[{"given":"Ya","family":"Jiang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Maocheng","family":"Hu","sequence":"additional","affiliation":[{"name":"National Intelligent Voice Innovation Center,Hefei,China"}]},{"given":"Pengfei","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Zeyan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Shi","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Zhaoxu","family":"Nian","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Yuxuan","family":"Dong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Mingqi","family":"Cai","sequence":"additional","affiliation":[{"name":"National Intelligent Voice Innovation Center,Hefei,China"}]},{"given":"Xin","family":"Fang","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,China"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2470216"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref3","first-page":"1317","article-title":"Two-source acoustic event detection and localization: Online implementation in a smart-room","volume-title":"IEEE EURASIP Europ. Signal Process. Conf. (EUSIPCO)","author":"Butko"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.906694"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054090"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3019646"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047233"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746384"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2937185"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3226330"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01029"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094681"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"key":"ref22","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Int. Conf. Learn. Represent","author":"Zhang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref26","article-title":"The nerc-slip system for sound event localization and detection of dcase2023 challenge","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Wang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-592"},{"key":"ref28","article-title":"Starss23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","author":"Shimada","year":"2023"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687782.pdf?arnumber=10687782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:39:36Z","timestamp":1727764776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687782","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}