{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:20:56Z","timestamp":1772907656231,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2020AAA0105702"],"award-info":[{"award-number":["2020AAA0105702"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225207"],"award-info":[{"award-number":["62225207"]}],"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":["U19B2038"],"award-info":[{"award-number":["U19B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2019-025"],"award-info":[{"award-number":["GXXT-2019-025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3226328","type":"journal-article","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T18:48:17Z","timestamp":1671216497000},"page":"7711-7725","source":"Crossref","is-referenced-by-count":40,"title":["Semantic and Relation Modulation for Audio-Visual Event Localization"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3138-0734","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0478-7018","authenticated-orcid":false,"given":"Xuejin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.52"},{"key":"ref4","article-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Montes"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.137"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00406"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref15","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref16","first-page":"1866","article-title":"Unsupervised learning of spoken language with visual context","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Harwath"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00947"},{"key":"ref18","article-title":"Co-training of audio and video representations from self-supervised temporal synchronization","author":"Korbar","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268967"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref22","first-page":"2518","article-title":"Weakly supervised representation learning for unsynchronized audio-visual events","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Parekh"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137988"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref26","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01029"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240526"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.93"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.335"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132058"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3090167"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5220\/0010868900003124"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"ref60","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref63","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref66","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andrew"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3127029"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09990903.pdf?arnumber=9990903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T11:47:18Z","timestamp":1706788038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9990903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":70,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3226328","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}