{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:03:15Z","timestamp":1792688595323,"version":"4.5.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683226","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"2002-2006","source":"Crossref","is-referenced-by-count":116,"title":["Dual-modality Seq2Seq Network for Audio-visual Event Localization"],"prefix":"10.1109","author":[{"given":"Yan-Bo","family":"Lin","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Jhe","family":"Li","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref12","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref14","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","article-title":"Objects that sound","author":"arandjelovi?","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref3","article-title":"Learning to localize sound source in visual scenes","author":"senocak","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref5","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.538"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.389"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref9","article-title":"Efficient large-scale multi-modal classification","author":"kiela","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"ref20","article-title":"Lstm: A search space odyssey","author":"greff","year":"2015","journal-title":"CoRR"},{"key":"ref22","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref21","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"CoRR"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683226.pdf?arnumber=8683226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:19:04Z","timestamp":1755800344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683226","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}