{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:20:55Z","timestamp":1725808855305},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446516","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7845-7849","source":"Crossref","is-referenced-by-count":0,"title":["TransAVS: End-to-End Audio-Visual Segmentation with Transformer"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Ling","sequence":"first","affiliation":[{"name":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Data Science,China"}]},{"given":"Yuxi","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent,Youtu Lab"}]},{"given":"Zhenye","family":"Gan","sequence":"additional","affiliation":[{"name":"Tencent,Youtu Lab"}]},{"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Mingmin","family":"Chi","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Data Science,China"}]},{"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-005-2376-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref4","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"Aytar","year":"2016","journal-title":"PAM1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"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","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing","author":"Lin","year":"2021","journal-title":"NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_25"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3361862"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01875-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref23","article-title":"Making a case for 3d convolutions for object segmentation in videos","author":"Mahadevan","year":"2020","journal-title":"BMVC"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref25","article-title":"Transformer transforms salient object detection and camouflaged object detection","author":"Mao","year":"2021","journal-title":"CoRR"},{"key":"ref26","article-title":"Learning generative vision transformer with energy-based latent space for saliency prediction","author":"Zhang","year":"2021","journal-title":"N1PS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref28","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"N1PS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref34","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446516.pdf?arnumber=10446516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:19:43Z","timestamp":1722575983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446516\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446516","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}