{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:52:30Z","timestamp":1781088750056,"version":"3.54.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Fund of China","doi-asserted-by":"publisher","award":["61806094"],"award-info":[{"award-number":["61806094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Fund of China","doi-asserted-by":"publisher","award":["U1713208"],"award-info":[{"award-number":["U1713208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3106814","type":"journal-article","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:36:36Z","timestamp":1630701396000},"page":"7878-7888","source":"Crossref","is-referenced-by-count":20,"title":["Discriminative Cross-Modality Attention Network for Temporal Inconsistent Audio-Visual Event Localization"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4633-2794","authenticated-orcid":false,"given":"Hanyu","family":"Xuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Cross-modal embeddings for video and audio retrieval","author":"sur\u00eds","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/957142.957143"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2502248"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247923"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref35","first-page":"1806","article-title":"Multi-modal distance metric learning","author":"xie","year":"2013","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"key":"ref34","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc NIPS"},{"key":"ref28","first-page":"801","article-title":"Ambient sound provides supervision for visual learning","author":"owens","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref29","first-page":"631","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8030292"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178840"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451843"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/35048669"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2307\/1420397"},{"key":"ref26","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref10","first-page":"25","article-title":"On attention modules for audio-visual synchronization","author":"khosravan","year":"2019","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2896952"},{"key":"ref12","first-page":"2518","article-title":"Weakly supervised representation learning for unsynchronized audio-visual events","author":"parekh","year":"2018","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2823900"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.28"},{"key":"ref17","first-page":"1","article-title":"Multi-view canonical correlation analysis","author":"rupnik","year":"2010","journal-title":"Proc Conf Data Mining Data Warehouses (SiKDD)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2435740"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref4","first-page":"247","article-title":"Audio-visual event localization in unconstrained videos","author":"tian","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2018.1561793"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"baltru\u0161aitis","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref5","first-page":"279","article-title":"Cross-modal attention network for temporal inconsistent audio-visual event localization","author":"hanyu","year":"2020","journal-title":"Proc Assoc Adv Artif Intell (AAAI)"},{"key":"ref8","first-page":"6115","article-title":"Lip-reading with long short-term memory","author":"wand","year":"2016","journal-title":"Proc Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683453"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref9","article-title":"LipNet: End-to-end sentence-level lipreading","author":"assael","year":"2016","journal-title":"arXiv 1611 01599"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.524"},{"key":"ref47","first-page":"1083","article-title":"On deep multi-view representation learning","author":"wang","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"ref44","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"arXiv 1703 03130"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301387"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09528934.pdf?arnumber=9528934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:07Z","timestamp":1652194207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9528934\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3106814","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}