{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:10:58Z","timestamp":1776442258300,"version":"3.51.2"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/avss61716.2024.10672591","type":"proceedings-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T17:51:42Z","timestamp":1726681902000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Text-Guided Multi-Modal Fusion for Underwater Visual Tracking"],"prefix":"10.1109","author":[{"given":"Yonathan","family":"Michael","sequence":"first","affiliation":[{"name":"Khalifa University,Department of Electrical Engineering and Computer Science,Abu Dhabi,United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamad","family":"Alansari","sequence":"additional","affiliation":[{"name":"Khalifa University,Department of Electrical Engineering and Computer Science,Abu Dhabi,United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sajid","family":"Javed","sequence":"additional","affiliation":[{"name":"Khalifa University,Department of Electrical Engineering and Computer Science,Abu Dhabi,United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improving underwater visual tracking with a large scale dataset and image enhancement","author":"Alawode","year":"2023","journal-title":"arXiv preprint arXiv:2308.15816"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref5","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume":"35","author":"Guo","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref7","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv:2301.12597"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"ref9","first-page":"16743","article-title":"Swintrack: A simple and strong baseline for transformer tracking","volume":"35","author":"Lin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref12","article-title":"Gpt-4 technical report","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"}],"event":{"name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,16]]}},"container-title":["2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10672516\/10672563\/10672591.pdf?arnumber=10672591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T07:07:29Z","timestamp":1726729649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10672591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/avss61716.2024.10672591","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}