{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:53:00Z","timestamp":1777567980313,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"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":[[2024,10,27]]},"DOI":"10.1109\/icip51287.2024.10647485","type":"proceedings-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:34:45Z","timestamp":1727462085000},"page":"2480-2486","source":"Crossref","is-referenced-by-count":7,"title":["Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation"],"prefix":"10.1109","author":[{"given":"Juhyeong","family":"Seon","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"}]},{"given":"Woobin","family":"Im","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"}]},{"given":"Sebin","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"}]},{"given":"Jumin","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"}]},{"given":"Sung-Eui","family":"Yoon","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Annotationfree audio-visual segmentation","volume-title":"Proc. WACV","author":"Liu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref4","article-title":"Segment anything in 3d with nerfs","author":"Cen","year":"2023","journal-title":"arXiv preprint arXiv:2304.12308"},{"key":"ref5","article-title":"Anything-3d: Towards single-view anything reconstruction in the wild","author":"Shen","year":"2023","journal-title":"arXiv preprint arXiv:2304.10261"},{"key":"ref6","article-title":"Medical sam adapter: Adapting segment anything model for medical image segmentation","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv:2304.12620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref8","article-title":"Detect any shadow: Segment anything for video shadow detection","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2305.16698"},{"key":"ref9","first-page":"arXiv-2306","article-title":"Sam-helps-shadow: When segment anything model meet shadow removal","author":"Zhang","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref10","article-title":"Segment and track anything","author":"Cheng","year":"2023","journal-title":"arXiv preprint arXiv:2305.06558"},{"key":"ref11","article-title":"Refsam: Efficiently adapting segmenting anything model for referring video object segmentation","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv:2307.00997"},{"key":"ref12","article-title":"Segment anything meets point tracking","author":"Raji\u010d","year":"2023","journal-title":"arXiv preprint arXiv:2307.01197"},{"key":"ref13","article-title":"Av-sam: Segment anything model meets audio-visual localization and segmentation","author":"Mo","year":"2023","journal-title":"arXiv preprint arXiv:2305.01836"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref15","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","author":"Houlsby","year":"2019","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612373"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/97"},{"key":"ref19","article-title":"Avsegformer: Audio-visual segmentation with transformer","author":"Gao","year":"2023","journal-title":"arXiv preprint arXiv:2307.01146"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref21","article-title":"Contrastive conditional latent diffusion for audio-visual segmentation","author":"Mao","year":"2023","journal-title":"arXiv preprint arXiv:2307.16579"},{"key":"ref22","article-title":"Soundnet: Learning sound representations from unlabeled video","volume":"29","author":"Aytar","year":"2016","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"ref27","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2303.05499"},{"key":"ref28","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00278"}],"event":{"name":"2024 IEEE International Conference on Image Processing (ICIP)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,27]]},"end":{"date-parts":[[2024,10,30]]}},"container-title":["2024 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10647221\/10647122\/10647485.pdf?arnumber=10647485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T05:51:00Z","timestamp":1727502660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10647485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icip51287.2024.10647485","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]}}}