{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:11:09Z","timestamp":1777871469541,"version":"3.51.4"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.115839","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T01:56:46Z","timestamp":1775181406000},"page":"115839","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["RD-UOD: A novel dual-branch RGB-depth fusion network for underwater object detection"],"prefix":"10.1016","volume":"342","author":[{"given":"Yuanjia","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2150-7882","authenticated-orcid":false,"given":"Xiaobing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuchun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0888-8828","authenticated-orcid":false,"given":"Lingbo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115839_bib0001","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8205","article-title":"Mamba-YOLO: a simple baseline for object detection with state space model","volume":"39","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.115839_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110435","article-title":"UnitModule: a lightweight joint image enhancement module for underwater object detection","volume":"151","author":"Liu","year":"2024","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.knosys.2026.115839_bib0003","doi-asserted-by":"crossref","first-page":"2388","DOI":"10.1109\/TPAMI.2024.3524377","article-title":"Hyper-YOLO: when visual object detection meets hypergraph computation","volume":"47","author":"Feng","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115839_bib0004","series-title":"Proceedings of the International Conference on Learning Representations (ICLR)","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115839_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.107378","article-title":"MSRT-DETR: a novel RT-DETR model with multi-scale feature sequence for cell detection","volume":"103","author":"Zhou","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.knosys.2026.115839_bib0006","series-title":"Advances in Neural Information Processing Systems 36 (NeurIPS 2023)","article-title":"VanillaNet: the power of minimalism in deep learning","author":"Chen","year":"2023"},{"key":"10.1016\/j.knosys.2026.115839_bib0007","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"17773","article-title":"TransNeXt: robust foveal visual perception for vision transformers","author":"Shi","year":"2024"},{"issue":"5","key":"10.1016\/j.knosys.2026.115839_bib0008","doi-asserted-by":"crossref","first-page":"3509","DOI":"10.1109\/TPAMI.2023.3342120","article-title":"CenterNet++ for object detection","volume":"46","author":"Duan","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115839_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1090","article-title":"TransFusion: robust LiDAR-camera fusion for 3D object detection with transformers","author":"Bai","year":"2022"},{"key":"10.1016\/j.knosys.2026.115839_bib0010","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2774","article-title":"BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.115839_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"883","article-title":"Cross-modal transformer: towards fast and robust 3D object detection","author":"Zhang","year":"2022"},{"key":"10.1016\/j.knosys.2026.115839_bib0012","article-title":"DeepInteraction++: multi-modality interaction for autonomous driving","author":"Yang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115839_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1039","article-title":"Long-tailed 3D detection via multi-modal late fusion","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.115839_bib0014","series-title":"Proceedings of the IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","first-page":"1","article-title":"A dataset and benchmark of underwater object detection for robot picking","author":"Liu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115839_bib0015","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.neucom.2022.10.039","article-title":"Rethinking general underwater object detection: datasets, challenges, and solutions","volume":"517","author":"Fu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2026.115839_bib0016","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.neucom.2023.01.053","article-title":"Achieving domain generalization in underwater object detection by domain mixup and contrastive learning","volume":"528","author":"Chen","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2026.115839_bib0017","series-title":"2025 IEEE International Conference on Real-time Computing and Robotics (RCAR)","first-page":"1040","article-title":"You sense only once beneath: ultra-light real-Time underwater object detection","author":"Dong","year":"2025"},{"key":"10.1016\/j.knosys.2026.115839_bib0018","first-page":"1","article-title":"U-DECN: end-to-end underwater object detection ConvNet with improved denoising training","volume":"63","author":"Liu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"Part A","key":"10.1016\/j.knosys.2026.115839_bib0019","article-title":"Noise-aware state-space method for underwater object detection","volume":"172","author":"Zhou","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.115839_bib0020","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7659","article-title":"AMSP-UOD: when vortex convolution and stochastic perturbation meet underwater object detection","volume":"38","author":"Zhou","year":"2024"},{"key":"10.1016\/j.knosys.2026.115839_bib0021","series-title":"Proceedings of the 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","first-page":"1","article-title":"AquaFeat: a features-Based image enhancement model for underwater object detection","author":"Silva","year":"2025"},{"key":"10.1016\/j.knosys.2026.115839_bib0022","doi-asserted-by":"crossref","unstructured":"J. Zhou, Z. He, D. Zhang, S. Liu, X. Fu, X. Li, Spatial residual for underwater object detection, (2025) 4996\u20135013.","DOI":"10.1109\/TPAMI.2025.3548652"},{"key":"10.1016\/j.knosys.2026.115839_bib0023","series-title":"Pattern Recognition","first-page":"236","article-title":"DEYOLO: dual-feature-enhancement YOLO for cross-modality object detection","author":"Chen","year":"2024"},{"key":"10.1016\/j.knosys.2026.115839_bib0024","article-title":"A dual-branch joint learning network for underwater object detection","author":"Wang","year":"2024","journal-title":"Knowl. Based Syst."},{"issue":"2","key":"10.1016\/j.knosys.2026.115839_bib0025","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1109\/JOE.2025.3529121","article-title":"AO-UOD: a novel paradigm for underwater object detection using acousto-optic fusion","volume":"50","author":"Yu","year":"2025","journal-title":"IEEE J. Oceanic Eng."},{"issue":"4","key":"10.1016\/j.knosys.2026.115839_bib0026","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1002\/rob.22432","article-title":"UAMFDet: acoustic-optical fusion for underwater multi-modal object detection","volume":"42","author":"Chen","year":"2025","journal-title":"J. Field Rob."},{"key":"10.1016\/j.knosys.2026.115839_bib0027","series-title":"European Conference on Computer Vision","first-page":"293","article-title":"Hpff: hierarchical locally supervised learning with patch feature fusion","author":"Su","year":"2024"},{"key":"10.1016\/j.knosys.2026.115839_bib0028","article-title":"Unsupervised lifelong person re-identification via affinity harmonization","author":"Tan","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.knosys.2026.115839_bib0029","doi-asserted-by":"crossref","unstructured":"W. Lu, S.-B. Chen, H.-D. Li, Q.-L. Shu, C.H.Q. Ding, J. Tang, B. Luo, LEGNet: A lightweight edge-Gaussian driven network for low-quality remote sensing image object detection, (2025). https:\/\/arxiv.org\/abs\/2503.14012.","DOI":"10.1109\/ICCVW69036.2025.00299"},{"key":"10.1016\/j.knosys.2026.115839_bib0030","series-title":"Frontiers in Artificial Intelligence and Applications","first-page":"435","article-title":"EdgeNAT: transformer for efficient edge detection","volume":"392","author":"Jie","year":"2024"},{"key":"10.1016\/j.knosys.2026.115839_bib0031","unstructured":"Q. Hong, H. Jiang, P. Xiao, S. Du, T. Li, EDCSSM: edge detection with convolutional state space model, 2024, 2409.01609."},{"key":"10.1016\/j.knosys.2026.115839_bib0032","doi-asserted-by":"crossref","first-page":"9385","DOI":"10.1109\/TMM.2025.3613125","article-title":"Tensor completion framework by graph refinement for incomplete multi-view clustering","volume":"27","author":"Wang","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.115839_bib0033","unstructured":"H. Nakamura, H. Iino, M. Okada, T. Taniguchi, EasyControlEdge: a foundation-model fine-tuning for edge detection, 2026. 2602.16238."},{"key":"10.1016\/j.knosys.2026.115839_bib0034","series-title":"Pattern Recognition and Computer Vision - 6th Chinese Conference, PRCV 2023, Proceedings","first-page":"343","article-title":"DuAT: dual-aggregation transformer network for medical image segmentation","volume":"14429","author":"Tang","year":"2023"},{"key":"10.1016\/j.knosys.2026.115839_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"390","article-title":"CSPNet: a new backbone that can enhance learning capability of CNN","author":"Wang","year":"2020"},{"key":"10.1016\/j.knosys.2026.115839_bib0036","unstructured":"R. Khanam, M. Hussain, YOLOv11: an overview of the key architectural enhancements, 2024, 2410.17725."},{"key":"10.1016\/j.knosys.2026.115839_bib0037","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"32","article-title":"Going deeper with image transformers","author":"Touvron","year":"2021"},{"issue":"56","key":"10.1016\/j.knosys.2026.115839_bib0038","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.115839_bib0039","series-title":"European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)","first-page":"443","article-title":"No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects","volume":"13715","author":"Sunkara","year":"2022"},{"key":"10.1016\/j.knosys.2026.115839_bib0040","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1426","article-title":"Omni-kernel network for image restoration","volume":"38","author":"Cui","year":"2024"},{"key":"10.1016\/j.knosys.2026.115839_bib0041","series-title":"Computer Vision \u2013 ECCV 2014: 13th European Conference","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.knosys.2026.115839_bib0042","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9789","article-title":"TOOD: task-aligned one-stage object detection","author":"Chen","year":"2021"},{"key":"10.1016\/j.knosys.2026.115839_bib0043","series-title":"Advances in Neural Information Processing Systems","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015"},{"key":"10.1016\/j.knosys.2026.115839_bib0044","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6154","article-title":"Cascade R-CNN: delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.knosys.2026.115839_bib0045","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7389","article-title":"FoveaBox: beyond anchor-based object detection","author":"Kong","year":"2019"},{"key":"10.1016\/j.knosys.2026.115839_bib0046","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11943","article-title":"NAS-FCOS: fast neural architecture search for object detection","author":"Wang","year":"2020"},{"key":"10.1016\/j.knosys.2026.115839_bib0047","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"10.1016\/j.knosys.2026.115839_bib0048","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9308","article-title":"Deformable ConvNets v2: more deformable, better results","author":"Zhu","year":"2019"},{"key":"10.1016\/j.knosys.2026.115839_bib0049","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6982","article-title":"Generalized hinge loss for object detection","author":"Li","year":"2020"},{"key":"10.1016\/j.knosys.2026.115839_bib0050","series-title":"Proceedings of the International Conference on Machine Learning (ICML)","first-page":"6105","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.knosys.2026.115839_bib0051","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6568","article-title":"TridentNet: retrieving more useful descriptors for object detection","author":"Chen","year":"2019"},{"key":"10.1016\/j.knosys.2026.115839_bib0052","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"558","article-title":"VFNet: towards more robust and efficient general object detection","author":"Zhou","year":"2020"},{"issue":"8","key":"10.1016\/j.knosys.2026.115839_bib0053","article-title":"Lightweight small object detection algorithm based on STD-DETR","volume":"62","author":"Yin","year":"2025","journal-title":"Laser Optoelectron. Progress"},{"key":"10.1016\/j.knosys.2026.115839_bib0054","unstructured":"S. Soudeep, M. F. Mridha, M. A. Jahin, N. Dey, DGNN-YOLO: interpretable dynamic graph neural networks with YOLO11 for detecting and tracking small occluded objects in urban traffic, arXiv preprint abs\/2411.17251 (2024). https:\/\/arxiv.org\/abs\/2411.17251."},{"key":"10.1016\/j.knosys.2026.115839_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110222","article-title":"A gated cross-domain collaborative network for underwater object detection","volume":"149","author":"Dai","year":"2024","journal-title":"Pattern Recognit."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005654?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005654?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:17:17Z","timestamp":1777569437000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126005654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":55,"alternative-id":["S0950705126005654"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115839","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RD-UOD: A novel dual-branch RGB-depth fusion network for underwater object detection","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115839","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115839"}}