{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:25:35Z","timestamp":1778171135148,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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","award":["61971186"],"award-info":[{"award-number":["61971186"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906064"],"award-info":[{"award-number":["61906064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of\u00a0Hunan Province","doi-asserted-by":"publisher","award":["2020JJ5082"],"award-info":[{"award-number":["2020JJ5082"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project Program of State Key Laboratory of Virtual Reality Technology"},{"name":"Systems, Beihang University","award":["VRLAB2020B09"],"award-info":[{"award-number":["VRLAB2020B09"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2021.3127029","type":"journal-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T22:10:14Z","timestamp":1637014214000},"page":"418-429","source":"Crossref","is-referenced-by-count":41,"title":["Audio-Visual Event Localization by Learning Spatial and Semantic Co-Attention"],"prefix":"10.1109","volume":"25","author":[{"given":"Cheng","family":"Xue","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7533-2347","authenticated-orcid":false,"given":"Xionghu","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6688-3710","authenticated-orcid":false,"given":"Minjie","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9857-6283","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Vision Speech and Signal Processing, Department of Electrical and Electronic Engineering, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886263"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204264"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1207\/s15326969eco0501_1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2009.06.060"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref13","article-title":"See, hear, and read: Deep aligned representations","author":"Aytar","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref15","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aytar","year":"2016"},{"key":"ref16","first-page":"7763","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Korbar","year":"2018"},{"key":"ref17","first-page":"813","article-title":"Audio vision: Using audio-visual synchrony to locate sounds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hershey","year":"2000"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2296173"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2377515"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2937185"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240571"},{"key":"ref26","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chorowski","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461392"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2930913"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053427"},{"key":"ref31","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref36","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2277"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref43","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andrew","year":"2013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref45","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever","year":"2014"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-011-0841-3"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09615027.pdf?arnumber=9615027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:26:07Z","timestamp":1705026367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9615027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3127029","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}