{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T04:40:14Z","timestamp":1780461614474,"version":"3.54.1"},"reference-count":54,"publisher":"World Scientific Pub Co Pte Ltd","issue":"07","funder":[{"name":"Ministry of Education of Humanities and Social Science","award":["24YJAZH092"],"award-info":[{"award-number":["24YJAZH092"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["30923011022"],"award-info":[{"award-number":["30923011022"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20231454"],"award-info":[{"award-number":["BK20231454"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176183"],"award-info":[{"award-number":["62176183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2026,6,15]]},"abstract":"<jats:p>Underwater object detection plays a crucial role in marine resource exploration and ecological conservation. However, it suffers from significant challenges due to severe image blurring and low contrast, which substantially degrade the detection performance. To overcome these limitations, we propose DAF-DETR, a novel Detection Transformer framework with Dual Attention and Dual Fusion Modules (DFMs). DAF-DETR first introduces an Aggregated Attention Mechanism to enhance the ResNet residual blocks, which boosts both global context awareness and local detail extraction in the backbone network. Second, it incorporates a Deformable Attention-based Feature Interaction (DAFI) module to improve the discriminability between object and background features in low-contrast underwater images. Finally, a DFM, which integrates Global-to-Local Spatial Aggregation (GLSA) with Haar Wavelet-based Downsampling (HWD), is employed to effectively alleviate the adverse effects of severe underwater blurring. Extensive experiments on the DUO and Underwater Object Detection Dataset (UODD) datasets validate the effectiveness and robustness of the proposed DAF-DETR framework, demonstrating significant improvements over existing methods.<\/jats:p>","DOI":"10.1142\/s021800142652004x","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T03:03:46Z","timestamp":1770174226000},"source":"Crossref","is-referenced-by-count":1,"title":["DAF-DETR: Dual-Attention and Dual-Fusion DETR for Underwater Object Detection"],"prefix":"10.1142","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9364-8989","authenticated-orcid":false,"given":"Xiaopeng","family":"Liu","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, No. 579 Qianwangang Road, Qingdao 266590, Shandong, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3201-6586","authenticated-orcid":false,"given":"Keke","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, No. 579 Qianwangang Road, Qingdao 266590, Shandong, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6859-4173","authenticated-orcid":false,"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Science, Nanjing University of Science and Technology, Nanjing 210094, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8552-859X","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Medical Physics and Biomedical Engineering, University College London, Charles Bell House, 43\u201345 Foley Street, London W1W 7TY, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"219","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"S021800142652004XBIB001","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"S021800142652004XBIB002","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10788-1"},{"key":"S021800142652004XBIB003","doi-asserted-by":"publisher","DOI":"10.3390\/rs15041076"},{"key":"S021800142652004XBIB004","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475351"},{"key":"S021800142652004XBIB005","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108926"},{"key":"S021800142652004XBIB006","first-page":"9355","volume-title":"Proc. 35th Conf. Neural Information Processing Systems (NeurIPS 2021)","author":"Chu X.","year":"2021"},{"key":"S021800142652004XBIB007","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"S021800142652004XBIB008","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271644"},{"key":"S021800142652004XBIB009","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024.101971"},{"key":"S021800142652004XBIB010","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123253"},{"key":"S021800142652004XBIB011","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"S021800142652004XBIB012","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111111"},{"key":"S021800142652004XBIB013","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2019.106644"},{"key":"S021800142652004XBIB014","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124978"},{"key":"S021800142652004XBIB015","doi-asserted-by":"publisher","DOI":"10.3390\/rs14184487"},{"key":"S021800142652004XBIB016","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.116088"},{"key":"S021800142652004XBIB017","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475563"},{"key":"S021800142652004XBIB018","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3547007"},{"key":"S021800142652004XBIB019","doi-asserted-by":"publisher","DOI":"10.3390\/jmse10040469"},{"key":"S021800142652004XBIB020","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"S021800142652004XBIB021","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897515"},{"key":"S021800142652004XBIB022","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"S021800142652004XBIB023","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053829"},{"key":"S021800142652004XBIB024","first-page":"1","volume-title":"IEEE Int. Conf. Multimedia & Expo Workshops (ICMEW)","author":"Liu C.","year":"2021"},{"key":"S021800142652004XBIB025","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"S021800142652004XBIB026","doi-asserted-by":"publisher","DOI":"10.3390\/s23052567"},{"key":"S021800142652004XBIB027","unstructured":"Z. Liu, B. Wang and Y. Li, U-DECN: End-to-end underwater object detection, preprint (2024), arXiv:2408.05780."},{"key":"S021800142652004XBIB028","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110435"},{"key":"S021800142652004XBIB029","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107766"},{"key":"S021800142652004XBIB030","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"S021800142652004XBIB031","first-page":"363","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","author":"Sang H.","year":"2023"},{"key":"S021800142652004XBIB032","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08781-w"},{"key":"S021800142652004XBIB033","first-page":"17773","volume-title":"Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition","author":"Shi D.","year":"2024"},{"key":"S021800142652004XBIB034","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.01.088"},{"key":"S021800142652004XBIB035","first-page":"343","volume-title":"Proc. Chinese Conf. Pattern Recognition and Computer Vision (PRCV)","author":"Tang F.","year":"2023"},{"key":"S021800142652004XBIB036","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111672"},{"key":"S021800142652004XBIB037","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"S021800142652004XBIB038","doi-asserted-by":"publisher","DOI":"10.3390\/s23073367"},{"key":"S021800142652004XBIB039","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"S021800142652004XBIB040","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109819"},{"key":"S021800142652004XBIB041","doi-asserted-by":"publisher","DOI":"10.3390\/s22155492"},{"key":"S021800142652004XBIB042","unstructured":"J. Yang, C. Li, P. Zhang, X. Dai, B. Xiao, L. Yuan and J. Gao, Focal self-attention for local-global interactions in vision transformers, preprint (2021), arXiv:2107.00641."},{"key":"S021800142652004XBIB043","first-page":"328","volume-title":"Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Yang Y.","year":"2023"},{"key":"S021800142652004XBIB044","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072414"},{"key":"S021800142652004XBIB045","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.116005"},{"key":"S021800142652004XBIB046","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"S021800142652004XBIB047","volume-title":"Proc. Int. Conf. Learning Representations","author":"Zhang H.","year":"2023"},{"key":"S021800142652004XBIB048","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"S021800142652004XBIB049","doi-asserted-by":"publisher","DOI":"10.3390\/rs13224706"},{"key":"S021800142652004XBIB050","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"S021800142652004XBIB051","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28599"},{"key":"S021800142652004XBIB052","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3548652"},{"key":"S021800142652004XBIB053","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102680"},{"key":"S021800142652004XBIB054","volume-title":"Proc. Int. Conf. Learning Representations (ICLR)","author":"Zhu X.","year":"2021"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S021800142652004X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:45:15Z","timestamp":1776843915000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S021800142652004X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":54,"journal-issue":{"issue":"07","published-print":{"date-parts":[[2026,6,15]]}},"alternative-id":["10.1142\/S021800142652004X"],"URL":"https:\/\/doi.org\/10.1142\/s021800142652004x","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"value":"0218-0014","type":"print"},{"value":"1793-6381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]},"article-number":"2652004"}}