{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:47:56Z","timestamp":1776750476439,"version":"3.51.2"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20322"],"award-info":[{"award-number":["U24A20322"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576094"],"award-info":[{"award-number":["62576094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62461018"],"award-info":[{"award-number":["62461018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471278"],"award-info":[{"award-number":["62471278"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Big Data Computing Center of Southeast University","award":["625YXQN594"],"award-info":[{"award-number":["625YXQN594"]}]},{"name":"Innovation Platform for \u201cNew Star of South China Sea\u201d of Hainan Province","award":["NHXXRCXM202306"],"award-info":[{"award-number":["NHXXRCXM202306"]}]},{"name":"General Research Fund (GRF) of the Research Grants Council (RGC), Hong Kong Special Administrative Region","award":["13200425"],"award-info":[{"award-number":["13200425"]}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of Hong Kong Special Administrative Region","doi-asserted-by":"publisher","award":["STG5\/E-103\/24-R"],"award-info":[{"award-number":["STG5\/E-103\/24-R"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3682126","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T19:36:26Z","timestamp":1776195386000},"page":"4012-4026","source":"Crossref","is-referenced-by-count":0,"title":["ViT-UWA: Vision Transformer Underwater-Adapter for Dense Predictions Beneath the Water Surface"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3907-6550","authenticated-orcid":false,"given":"Yuheng","family":"Jia","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1631-6914","authenticated-orcid":false,"given":"Qirui","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Software Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0740-0691","authenticated-orcid":false,"given":"Hua","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9425-1553","authenticated-orcid":false,"given":"Yutong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7484-7261","authenticated-orcid":false,"given":"Sam","family":"Kwong","sequence":"additional","affiliation":[{"name":"School of Data Science, Lingnan University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0972-4008","authenticated-orcid":false,"given":"Runmin","family":"Cong","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.116088"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340821"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/rs14081818"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2022.1003568"},{"key":"ref6","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref8","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Xie"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref11","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv:2205.08534"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00525"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00126"},{"key":"ref14","first-page":"29545","article-title":"Diving into underwater: Segment anything model guided underwater salient instance segmentation and a large-scale dataset","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Lian"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref17","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref18","article-title":"BEiT v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv:2208.06366"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25147"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10499-024-01439-x"},{"key":"ref22","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref23","first-page":"5986","article-title":"BERT and pals: Projected attention layers for efficient adaptation in multi-task learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stickland"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01862"},{"key":"ref28","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3274988"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286263"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3177129"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2955241"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301226"},{"key":"ref35","article-title":"How do vision transformers work?","author":"Park","year":"2022","journal-title":"arXiv:2202.06709"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3354108"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref40","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref42","article-title":"Benchmarking detection transfer learning with vision transformers","author":"Li","year":"2021","journal-title":"arXiv:2111.11429"},{"key":"ref43","article-title":"Reversible column networks","author":"Cai","year":"2022","journal-title":"arXiv:2212.11696"},{"key":"ref44","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref48","volume-title":"MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark","year":"2020"},{"key":"ref49","volume-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results","author":"Everingham","year":"2012"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.07155"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref53","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Li"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref55","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref59","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref60","article-title":"Evaluation of segment anything model 2: The role of SAM2 in the underwater environment","author":"Lian","year":"2024","journal-title":"arXiv:2408.02924"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_27"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974710"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19944"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.01.056"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3009373"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3123066"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00357"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11481591.pdf?arnumber=11481591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:20:53Z","timestamp":1776748853000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11481591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3682126","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}