{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T17:06:42Z","timestamp":1784394402655,"version":"3.55.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3486344","type":"journal-article","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:29:52Z","timestamp":1729877392000},"page":"2398-2409","source":"Crossref","is-referenced-by-count":15,"title":["Bootstrapping Audio-Visual Video Segmentation by Strengthening Audio Cues"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7758-699X","authenticated-orcid":false,"given":"Tianxiang","family":"Chen","sequence":"first","affiliation":[{"name":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9095-4462","authenticated-orcid":false,"given":"Zhentao","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0026-6813","authenticated-orcid":false,"given":"Tao","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3028-0755","authenticated-orcid":false,"given":"Qi","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3977-8800","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-9316","authenticated-orcid":false,"given":"Nenghai","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6799-9416","authenticated-orcid":false,"given":"Le","family":"Lu","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, New York City, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445233"},{"key":"ref3","article-title":"Audio-visual segmentation with semantics","author":"Zhou","year":"2023","journal-title":"arXiv:2301.13190"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref7","article-title":"Audio-aware query-enhanced transformer for audio-visual segmentation","author":"Liu","year":"2023","journal-title":"arXiv:2307.13236"},{"key":"ref8","article-title":"BAVS: Bootstrapping audio-visual segmentation by integrating foundation knowledge","author":"Liu","year":"2023","journal-title":"arXiv:2308.10175"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3171983"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref15","article-title":"Contrastive conditional latent diffusion for audio-visual segmentation","author":"Mao","year":"2023","journal-title":"arXiv:2307.16579"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3384406"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/66"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00326"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27882"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3298644"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284165"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3345852"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3321977"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3461795"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3450954"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3298319"},{"key":"ref27","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref28","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv:2203.03605"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref35","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","article-title":"Making a case for 3D convolutions for object segmentation in videos","author":"Mahadevan","year":"2020","journal-title":"arXiv:2008.11516"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref39","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3469286"},{"key":"ref41","first-page":"15448","article-title":"Learning generative vision transformer with energy-based latent space for saliency prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref42","article-title":"Improving audio-visual segmentation with bidirectional generation","author":"Hao","year":"2023","journal-title":"arXiv:2308.08288"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10735252.pdf?arnumber=10735252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:51:15Z","timestamp":1741373475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10735252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":42,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3486344","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}