{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T19:09:06Z","timestamp":1767035346160,"version":"3.37.3"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428081","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T21:14:21Z","timestamp":1623273261000},"page":"1-6","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal Transformer Networks with Latent Interaction for Audio-Visual Event Localization"],"prefix":"10.1109","author":[{"given":"Yixuan","family":"He","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,Center for Future Media & School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Center for Future Media & School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Huaqiao University,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihua","family":"Ou","sequence":"additional","affiliation":[{"name":"Guizhou Normal University,School of Big Data and Computer Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[{"name":"Kyushu Institute of Technology,Department of Mechanical and Control Engineering,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref11","article-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers","author":"huang","year":"0","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref5","first-page":"892","article-title":"Sound- net: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref7","first-page":"2002","article-title":"Dualmodality seq2seq network for audio-visual event localization","author":"lin","year":"2019","journal-title":"ICASSP"},{"key":"ref2","first-page":"2002","article-title":"Dualmodality seq2seq network for audio-visual event localization","author":"lin","year":"2019","journal-title":"ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref9","first-page":"349","article-title":"Cross-modal attention network for temporal inconsistent audio-visual event localization","author":"xuan","year":"2017","journal-title":"ACM MM"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2021,7,5]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428081.pdf?arnumber=9428081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T21:28:01Z","timestamp":1656365281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428081","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}