{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:44:11Z","timestamp":1755798251080,"version":"3.44.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"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":[[2025,9,14]]},"DOI":"10.1109\/icip55913.2025.11084490","type":"proceedings-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:41:38Z","timestamp":1755546098000},"page":"2510-2515","source":"Crossref","is-referenced-by-count":0,"title":["Audio Visual Segmentation through Text Embeddings"],"prefix":"10.1109","author":[{"given":"Kyungbok","family":"Lee","sequence":"first","affiliation":[{"name":"University of Rochester,Department of Computer Science,Rochester,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"SAM 2: Segment anything in images and videos","year":"2024","author":"Ravi","key":"ref6"},{"article-title":"Prompting frameworks for large language models: A survey","year":"2023","author":"Liu","key":"ref7"},{"article-title":"Av-sam: Segment anything model meets audio-visual localization and segmentation","year":"2023","author":"Mo","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"ref10","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02636"},{"key":"ref14","article-title":"Samrs: Scaling-up remote sensing segmentation dataset with segment anything model","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"article-title":"EVF-SAM: Early vision-language fusion for text-prompted segment anything model","year":"2024","author":"Zhang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612373"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647485"},{"article-title":"SAVE: Segment audio-visual easy way using segment anything model","year":"2024","author":"Nguyen","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1086"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref26","article-title":"Segment anything in 3d with nerfs","author":"Cen","year":"2023","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2025,9,14]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2025,9,17]]}},"container-title":["2025 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11084272\/11083968\/11084490.pdf?arnumber=11084490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:00:28Z","timestamp":1755579628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icip55913.2025.11084490","relation":{},"subject":[],"published":{"date-parts":[[2025,9,14]]}}}