{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:43:22Z","timestamp":1791996202365,"version":"4.4.0"},"reference-count":122,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tnnls.2026.3657138","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:07:11Z","timestamp":1770671231000},"page":"3956-3969","source":"Crossref","is-referenced-by-count":6,"title":["AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6680-7948","authenticated-orcid":false,"given":"Basit","family":"Alawode","sequence":"first","affiliation":[{"name":"Khalifa University of Science and Technology","place":["Abu Dhabi, United Arab Emirates"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6312-5765","authenticated-orcid":false,"given":"Iyyakutti","family":"Iyappan Ganapathi","sequence":"additional","affiliation":[{"name":"Khalifa University of Science and Technology","place":["Abu Dhabi, United Arab Emirates"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0036-2875","authenticated-orcid":false,"given":"Sajid","family":"Javed","sequence":"additional","affiliation":[{"name":"Khalifa University of Science and Technology","place":["Abu Dhabi, United Arab Emirates"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"The University of Western Australia","place":["Perth, WA, Australia"],"department":["Department of Computer Science and Software Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5986-9876","authenticated-orcid":false,"given":"Arif","family":"Mahmood","sequence":"additional","affiliation":[{"name":"Information Technology University","place":["Lahore, Pakistan"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Marine Animal Images","year":"2023"},{"key":"ref2","volume-title":"Sea Animals Image Dataset","year":"2023"},{"key":"ref3","volume-title":"URPC Dataset","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3430899"},{"key":"ref5","first-page":"3326","article-title":"UTB180: A high-quality benchmark for underwater tracking","volume-title":"Proc. ACCV","author":"Alawode"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref7","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/03036758.2022.2101484"},{"key":"ref9","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref10","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/icesjms\/fsae089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01762-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-019-0689-x"},{"key":"ref18","first-page":"143","article-title":"PDFFigures 2.0: Mining figures from research papers","volume-title":"Proc. IEEE\/ACM Joint Conf. Digit. Libraries (JCDL)","author":"Clark"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref20","article-title":"Ocean acidification\u2019s impact on marine ecosystems","author":"Dell","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00044"},{"key":"ref22","volume-title":"Corals Classification","author":"Dighe","year":"2023"},{"issue":"4","key":"ref23","first-page":"56","article-title":"The wonders of coral reefs","volume":"245","author":"Doe","year":"2023","journal-title":"Nat. Geo."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-marine-041911-111611"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2146-7"},{"key":"ref26","article-title":"The decline of Australia\u2019s great barrier reef","author":"Evers","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3578516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1126\/science.abf0861"},{"key":"ref30","article-title":"Coral species classification dataset","author":"Ha","year":"2022"},{"key":"ref31","article-title":"MarineDet: Towards open-marine object detection","author":"Haixin","year":"2023","journal-title":"arXiv:2310.01931"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1126\/science.1149345"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2022.1071618"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3266163"},{"key":"ref36","first-page":"296","article-title":"Underwater image restoration based on convolutional neural network","volume-title":"Proc. ACML","author":"Hu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01740"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340821"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974710"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.048"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2020.101088"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/s0065-2881(08)60212-6"},{"key":"ref43","article-title":"The fishnet open images database: A dataset for fish detection and fine-grained categorization in fisheries","author":"Kay","year":"2021","journal-title":"arXiv:2106.09178"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01874"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/app14166888"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2730363"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1111\/raq.12726"},{"key":"ref50","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"ref52","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021","journal-title":"arXiv:2110.05208"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.115449"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/jmse12071132"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref61","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2018.05.048"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"ref64","first-page":"195","article-title":"Australasian freshwater fish faunas: Diversity, interrelationships, radiations and conservation","volume-title":"Evolution and Biogeography of Australasian Vertebrates","author":"Merrick","year":"2006"},{"key":"ref65","article-title":"The rich biodiversity of ocean ecosystems","author":"Michel","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8664785"},{"key":"ref67","article-title":"Innovative approaches to coral conservation","author":"Mohan","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1090"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01456"},{"key":"ref70","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2021.3086907"},{"key":"ref72","first-page":"18","article-title":"Detection of marine animals in a new underwater dataset with varying visibility","volume-title":"Proc. CVPRW","author":"Pedersen"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3276332"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICOECA62351.2024.00167"},{"key":"ref75","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-71639-x"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-025-03860-y"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1111\/faf.12666"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00814"},{"key":"ref81","volume-title":"Zoological Catalogue of Australia: Aves (Columbidae to Coraciidae)","volume":"37.2","author":"Schodde","year":"1997"},{"key":"ref82","article-title":"Deep learning for multi-label classification of coral conditions in the indo-pacific via underwater photogrammetry","author":"Shao","year":"2024","journal-title":"arXiv:2403.05930"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.11646\/zootaxa.4367.1.1"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2023.1174347"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1093\/icesjms\/fsx109"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01325"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref90","article-title":"Understanding coral bleaching and ocean health","author":"Thornton","year":"2024"},{"key":"ref91","article-title":"The vital role of coral reefs and the threats they face","author":"Thornton","year":"2024"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU50717.2020.9259867"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107069"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.11646\/zootaxa.3882.1.1"},{"key":"ref96","volume-title":"Corals of the World","author":"Veron","year":"2016"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3022878"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.02.018"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746215"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16408"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.01.056"},{"key":"ref102","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021","journal-title":"arXiv:2104.10157"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447513"},{"key":"ref104","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4 V(ision)","author":"Yang","year":"2023","journal-title":"arXiv:2309.17421"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072414"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747776"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475364"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1587"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00249"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124932"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475494"},{"key":"ref113","article-title":"Exploring boundary of GPT-4V on marine analysis: A preliminary case study","author":"Zheng","year":"2024","journal-title":"arXiv:2401.02147"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02661"},{"key":"ref115","article-title":"MarineGPT: Unlocking secrets of ocean to the public","author":"Zheng","year":"2023","journal-title":"arXiv:2310.13596"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00024"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.gsf.2022.101427"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01171"},{"key":"ref121","article-title":"CoralVOS: Dataset and benchmark for coral video segmentation","author":"Ziqiang","year":"2023","journal-title":"arXiv:2310.01946"},{"key":"ref122","first-page":"239","article-title":"Marineinst: A foundation model for marine image analysis with instance visual description","volume-title":"Proc. ECCV","author":"Ziqiang"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11643423\/11380196.pdf?arnumber=11380196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T19:17:00Z","timestamp":1786043820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11380196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":122,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2026.3657138","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}