{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T20:15:34Z","timestamp":1788466534834,"version":"build-2803163510"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100012906","name":"Shandong Provincial Education Department","doi-asserted-by":"publisher","award":["2024KJN033"],"award-info":[{"award-number":["2024KJN033"]}],"id":[{"id":"10.13039\/100012906","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.patrec.2026.08.005","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T23:33:59Z","timestamp":1786059239000},"page":"191-197","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["HANet: A multimodal hybrid attention network for underwater acoustic target classification"],"prefix":"10.1016","volume":"208","author":[{"given":"Ning","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengpeng","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manli","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2026.08.005_bib0001","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.apacoust.2016.06.008","article-title":"ShipsEar: an underwater vessel noise database","volume":"113","author":"Santos-Dom\u00ednguez","year":"2016","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.patrec.2026.08.005_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.115270","article-title":"DeepShip: an underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification","volume":"183","author":"Irfan","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patrec.2026.08.005_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2023.109725","article-title":"Self-supervised learning minimax entropy domain adaptation for the underwater target recognition","volume":"216","author":"Yang","year":"2024","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.patrec.2026.08.005_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2023.114926","article-title":"Underwater acoustic target recognition based on smoothness-inducing regularization and spectrogram-based data augmentation","volume":"281","author":"Xu","year":"2023","journal-title":"Ocean Eng."},{"key":"10.1016\/j.patrec.2026.08.005_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2023.109552","article-title":"Underwater acoustic target recognition based on spectrum component analysis of ship radiated noise","volume":"211","author":"Zhu","year":"2023","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.patrec.2026.08.005_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2024.109851","article-title":"Underwater acoustic target recognition method based on WA-DS decision fusion","volume":"217","author":"Feng","year":"2024","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.patrec.2026.08.005_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2021.107989","article-title":"Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentation","volume":"178","author":"Liu","year":"2021","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.patrec.2026.08.005_bib0008","first-page":"1","article-title":"A transformer-based deep learning network for underwater acoustic target recognition","volume":"19","author":"Feng","year":"2022","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"issue":"4","key":"10.1016\/j.patrec.2026.08.005_bib0009","first-page":"860","article-title":"Passive sonar automated target classifier for shallow waters using end-to-end learnable deep convolutional LSTMs","volume":"24","author":"Kamal","year":"2021","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"10.1016\/j.patrec.2026.08.005_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2020.3029584","article-title":"Underwater acoustic target classification based on dense convolutional neural network","volume":"19","author":"Doan","year":"2022","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.patrec.2026.08.005_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.apor.2025.104554","article-title":"End-to-end underwater acoustic target classification with frequency separation strategy","volume":"158","author":"Tang","year":"2025","journal-title":"Appl. Ocean Res."},{"key":"10.1016\/j.patrec.2026.08.005_bib0012","series-title":"Proc. Interspeech","first-page":"3604","article-title":"Multi-stream network with temporal attention for environmental sound classification","author":"Li","year":"2019"},{"issue":"11","key":"10.1016\/j.patrec.2026.08.005_bib0013","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/jmse7110380","article-title":"Joint representation and recognition for ship-radiated noise based on multimodal deep learning","volume":"7","author":"Yuan","year":"2019","journal-title":"J. Marine Sci. Eng."},{"key":"10.1016\/j.patrec.2026.08.005_bib0014","first-page":"1","article-title":"More modalities mean better: vessel target recognition and localization through symbiotic transformer and multiview regression","volume":"62","author":"Liu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"10.1016\/j.patrec.2026.08.005_bib0015","series-title":"Proc. Int. Conf. Comput. Big Data Artif. Intell.","first-page":"1","article-title":"Multi-modal underwater acoustic target recognition","volume":"63","author":"He","year":"2025"},{"key":"10.1016\/j.patrec.2026.08.005_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110119","article-title":"Joint learning model for underwater acoustic target recognition","volume":"260","author":"Tian","year":"2023","journal-title":"Knowl. Based Syst."},{"issue":"13","key":"10.1016\/j.patrec.2026.08.005_bib0017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/rs16132442","article-title":"A novel multi-feature fusion model based on pre-trained wav2vec 2.0 for underwater acoustic target recognition","volume":"16","author":"Pu","year":"2024","journal-title":"Remote Sens."},{"issue":"3","key":"10.1016\/j.patrec.2026.08.005_bib0018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LSENS.2025.3541593","article-title":"Underwater acoustic target classification using auditory fusion features and efficient convolutional attention network","volume":"9","author":"Yang","year":"2025","journal-title":"IEEE Sens. Lett."},{"issue":"6","key":"10.1016\/j.patrec.2026.08.005_bib0019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/jmse13061101","article-title":"A multi-time-frequency feature fusion approach for marine mammal sound recognition","volume":"13","author":"Meng","year":"2025","journal-title":"J. Marine Sci. Eng."},{"key":"10.1016\/j.patrec.2026.08.005_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2021.108261","article-title":"Integrated neural networks based on feature fusion for underwater target recognition","volume":"182","author":"Zhang","year":"2021","journal-title":"Appl. Acoust."},{"issue":"7","key":"10.1016\/j.patrec.2026.08.005_bib0021","doi-asserted-by":"crossref","first-page":"11416","DOI":"10.1109\/JSEN.2025.3538688","article-title":"A lightweight time\u2013frequency\u2013space dual-stream network for active sonar-based underwater target recognition","volume":"25","author":"Chen","year":"2025","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.patrec.2026.08.005_bib0022","first-page":"1","article-title":"Constructing a multi-modal based underwater acoustic target recognition method with a pre-Trained language-audio model","volume":"63","author":"Fu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"10.1016\/j.patrec.2026.08.005_bib0023","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.eswa.2019.06.040","article-title":"End-to-end environmental sound classification using a 1D convolutional neural network","volume":"136","author":"Abdoli","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patrec.2026.08.005_bib0024","unstructured":"K. Choi, G. Fazekas, K. Cho, M. Sandler, A tutorial on deep learning for music information retrieval, (2018) 1\u201316. arXiv: 1709.04396."},{"issue":"2","key":"10.1016\/j.patrec.2026.08.005_bib0025","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/JSTSP.2019.2908700","article-title":"Deep learning for audio signal processing","volume":"13","author":"Purwins","year":"2019","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.patrec.2026.08.005_bib0026","series-title":"Proc. Int. Conf. Mach. Learn. (ICML)","first-page":"10524","article-title":"On layer normalization in the transformer architecture","author":"Xiong","year":"2020"},{"key":"10.1016\/j.patrec.2026.08.005_bib0027","unstructured":"D. Hendrycks, K. Gimpel, Gaussian Error Linear Units (GELUs), (2016) 1\u201310. arXiv preprint arXiv: 1606.08415."},{"key":"10.1016\/j.patrec.2026.08.005_bib0028","series-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","first-page":"448","article-title":"Pay attention to MLPs","author":"Liu","year":"2021"},{"key":"10.1016\/j.patrec.2026.08.005_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2022.112626","article-title":"Adaptive ship-radiated noise recognition with learnable fine-grained wavelet transform","volume":"265","author":"Xie","year":"2022","journal-title":"Ocean Eng."},{"key":"10.1016\/j.patrec.2026.08.005_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2023.115784","article-title":"An attention-based multi-scale convolution network for intelligent underwater acoustic signal recognition","volume":"287","author":"Zhou","year":"2023","journal-title":"Ocean Eng."},{"key":"10.1016\/j.patrec.2026.08.005_bib0031","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patrec.2026.08.005_bib0032","series-title":"Proc. Int. Conf. Mach. Learn. (ICML)","first-page":"6105","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","volume":"97","author":"Tan","year":"2019"},{"key":"10.1016\/j.patrec.2026.08.005_bib0033","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"10428","article-title":"Designing network design spaces","author":"Radosavovic","year":"2020"},{"key":"10.1016\/j.patrec.2026.08.005_bib0034","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.patrec.2026.08.005_bib0035","series-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","first-page":"1","article-title":"Patches are all you need?","author":"Trockman","year":"2022"},{"key":"10.1016\/j.patrec.2026.08.005_bib0036","series-title":"Proc. Interspeech","first-page":"2753","article-title":"Efficient training of audio transformers with patchout","author":"Koutini","year":"2022"},{"key":"10.1016\/j.patrec.2026.08.005_bib0037","article-title":"Underwater vessel sound recognition based on multi-layer feature and attention mechanism","volume":"15","author":"Wei","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.patrec.2026.08.005_bib0038","series-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP)","first-page":"2721","article-title":"Learning environmental sounds with end-to-end convolutional neural network","author":"Tokozume","year":"2017"},{"key":"10.1016\/j.patrec.2026.08.005_bib0039","series-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP)","first-page":"421","article-title":"Very deep convolutional neural networks for raw waveforms","author":"Dai","year":"2017"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016786552600276X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016786552600276X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T19:25:50Z","timestamp":1788463550000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S016786552600276X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":39,"alternative-id":["S016786552600276X"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.08.005","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HANet: A multimodal hybrid attention network for underwater acoustic target classification","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.08.005","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"}]}}