{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:25:50Z","timestamp":1761895550134,"version":"build-2065373602"},"reference-count":29,"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\/501100002369","name":"Chongqing University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002369","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\/icme59968.2025.11209557","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":["Cross-Modal Semantic-Aware Network for Audio-Visual Event Localization"],"prefix":"10.1109","author":[{"given":"Liang","family":"Liu","sequence":"first","affiliation":[{"name":"Chongqing University of Posts and Telecommunications,School of Computer Science and Technology,P. R. China,400065"}]},{"given":"Shuaiyong","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications,School of Automation,P. R. China,400065"}]},{"given":"Yongqiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications,School of Computer Science and Technology,P. R. China,400065"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1207\/s15326969eco0501_1"},{"key":"ref2","first-page":"arXiv:2208.09579","author":"Wei","year":"2022","journal-title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547869"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612506"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3324498"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3226328"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3150469"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270624"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"article-title":"Cross-modal prompts: adapting large pre-trained models for audio-visual downstream tasks","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst","author":"Duan","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3411045"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02142-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_22"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"issue":"86","key":"ref29","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"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\/11209557.pdf?arnumber=11209557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:52:43Z","timestamp":1761889963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209557","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}