Dual-stage learning framework for underwater acoustic target recognition with cross-attention mechanism and audio-guided contrastive learning

Underwater acoustic target recognition is crucial for marine exploration and environmental monitoring. However, the redundancy in raw time-domain signals and the challenges in effectively integrating time-frequency representations with audio features hinder current methods. To address these challeng...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 652; p. 131101
Main Authors: Zhao, Rongyao, Liu, Feng, Zhao, Lyufang, Li, Daihui, Xu, Jing, Liu, Yuanxin, Shen, Tongsheng
Format: Journal Article
Language:English
Published: Elsevier B.V 01.11.2025
Subjects:
ISSN:0925-2312
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Underwater acoustic target recognition is crucial for marine exploration and environmental monitoring. However, the redundancy in raw time-domain signals and the challenges in effectively integrating time-frequency representations with audio features hinder current methods. To address these challenges, we introduce a dual-stage learning framework, named audio-guided cross-attention dual-stage network for underwater acoustic target recognition (ACDN-UATR). The approach combines a cross-attention mechanism with audio-guided contrastive learning to improve recognition accuracy. In the first stage, a masked autoencoder (MAE) is used to learn and reconstruct time-frequency features, while a cross-attention mechanism efficiently fuses features from different spectrograms. In the second stage, contrastive learning is employed to align features extracted from time-frequency representations and raw audio signals, enhancing feature consistency and recognition robustness. Experimental results demonstrate that ACDN-UATR effectively integrates both time-frequency and audio-based features, achieving high recognition accuracy on the ShipsEar dataset. •Novel dual-stage learning framework (ACDN-UATR) proposed for UATR.•Cross-attention MAE fuses complementary Mel and CQT spectrogram features.•Audio-guided contrastive learning aligns multimodal acoustic features.•Integrates time-frequency representation learning with raw audio analysis.•Achieves superior underwater target recognition accuracy on ShipsEar dataset.
AbstractList Underwater acoustic target recognition is crucial for marine exploration and environmental monitoring. However, the redundancy in raw time-domain signals and the challenges in effectively integrating time-frequency representations with audio features hinder current methods. To address these challenges, we introduce a dual-stage learning framework, named audio-guided cross-attention dual-stage network for underwater acoustic target recognition (ACDN-UATR). The approach combines a cross-attention mechanism with audio-guided contrastive learning to improve recognition accuracy. In the first stage, a masked autoencoder (MAE) is used to learn and reconstruct time-frequency features, while a cross-attention mechanism efficiently fuses features from different spectrograms. In the second stage, contrastive learning is employed to align features extracted from time-frequency representations and raw audio signals, enhancing feature consistency and recognition robustness. Experimental results demonstrate that ACDN-UATR effectively integrates both time-frequency and audio-based features, achieving high recognition accuracy on the ShipsEar dataset. •Novel dual-stage learning framework (ACDN-UATR) proposed for UATR.•Cross-attention MAE fuses complementary Mel and CQT spectrogram features.•Audio-guided contrastive learning aligns multimodal acoustic features.•Integrates time-frequency representation learning with raw audio analysis.•Achieves superior underwater target recognition accuracy on ShipsEar dataset.
ArticleNumber 131101
Author Xu, Jing
Zhao, Lyufang
Liu, Yuanxin
Zhao, Rongyao
Liu, Feng
Li, Daihui
Shen, Tongsheng
Author_xml – sequence: 1
  givenname: Rongyao
  surname: Zhao
  fullname: Zhao, Rongyao
  email: 12434048@zju.edu.cn
  organization: Ocean College, Zhejiang University, Zhoushan, 316021, China
– sequence: 2
  givenname: Feng
  surname: Liu
  fullname: Liu, Feng
  email: liufeng_cv@126.com
  organization: National Innovation Institute of Defense Technology, PLA Academy of Military Science, Beijing, 100071, China
– sequence: 3
  givenname: Lyufang
  surname: Zhao
  fullname: Zhao, Lyufang
  email: 12034052@zju.edu.cn
  organization: Ocean College, Zhejiang University, Zhoushan, 316021, China
– sequence: 4
  givenname: Daihui
  surname: Li
  fullname: Li, Daihui
  email: lidh_ai@sina.com
  organization: National Innovation Institute of Defense Technology, PLA Academy of Military Science, Beijing, 100071, China
– sequence: 5
  givenname: Jing
  surname: Xu
  fullname: Xu, Jing
  email: jxu-optics@zju.edu.cn
  organization: Ocean College, Zhejiang University, Zhoushan, 316021, China
– sequence: 6
  givenname: Yuanxin
  surname: Liu
  fullname: Liu, Yuanxin
  email: bce18gru@163.com
  organization: National Innovation Institute of Defense Technology, PLA Academy of Military Science, Beijing, 100071, China
– sequence: 7
  givenname: Tongsheng
  orcidid: 0009-0006-6665-9299
  surname: Shen
  fullname: Shen, Tongsheng
  email: submit4z@163.com
  organization: Ocean College, Zhejiang University, Zhoushan, 316021, China
BookMark eNp9kM1OwzAQhH0oEm3hDTj4BVJsN6mbCxIqvxISFzhbG3udujQ2sp1WPATvTNoiceO0mpFmdvRNyMgHj4RccTbjjC-uNzOPvQ7dTDBRzficD-6IjFktqkLMuTgnk5Q2jHHJRT0m33c9bIuUoUW6RYje-ZbaCB3uQ_ygNkTae4NxDxkjBR36lJ2mGWKLmUbUofUuu-Dp3uU11TGkVEDO6I9mh3oN3qWOgjcUeuNC0fbOoKE6-BxhaNv9fb4gZxa2CS9_75S8P9y_rZ6Kl9fH59XtS6FFJXNhTbmwDa8kE9osRVNbKbWsQIIpkduGWW1wqUsJ0NQa6qaSUM6XjakHZfRyPiXlqfe4N6JVn9F1EL8UZ-qAUW3UCaM6YFQnjEPs5hTDYdvOYVRJO_QajRtIZGWC-7_gB9XSh7s
Cites_doi 10.1121/10.0026598
10.1016/j.oceaneng.2022.112626
10.1016/j.inffus.2017.02.007
10.1016/j.oceaneng.2022.112863
10.1121/10.0015053
10.1155/2018/6593037
10.1016/j.eswa.2024.123431
10.3390/s19051104
10.1016/j.oceaneng.2019.04.013
10.3390/e20120990
10.1016/j.oceaneng.2024.117252
10.1109/TASLP.2024.3358719
10.1016/j.apacoust.2016.06.008
10.1016/j.oceaneng.2024.120049
10.1109/79.689583
10.1016/j.apacoust.2021.107989
10.1109/LGRS.2020.3029584
10.1016/j.knosys.2022.110119
ContentType Journal Article
Copyright 2025 Elsevier B.V.
Copyright_xml – notice: 2025 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2025.131101
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
ExternalDocumentID 10_1016_j_neucom_2025_131101
S0925231225017734
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AATTM
AAXKI
AAXLA
AAXUO
AAYFN
AAYWO
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ACDAQ
ACGFS
ACLOT
ACRLP
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
AEBSH
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSN
SSV
SSZ
T5K
ZMT
~G-
~HD
29N
9DU
AAQXK
AAYXX
ABWVN
ABXDB
ACNNM
ACRPL
ADJOM
ADMUD
ADNMO
AGQPQ
ASPBG
AVWKF
AZFZN
CITATION
EJD
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
WUQ
XPP
ID FETCH-LOGICAL-c257t-fd46fb15702cd82b9f77c75a7ad4e1fb0fcde8c47aab9ca9b57a438bd99cadc83
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001543233800012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0925-2312
IngestDate Sat Nov 29 06:55:00 EST 2025
Sat Nov 29 17:08:56 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Underwater acoustic target recognition
Masked autoencoder
Dual-stage learning
Contrastive learning
Cross-attention mechanism
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c257t-fd46fb15702cd82b9f77c75a7ad4e1fb0fcde8c47aab9ca9b57a438bd99cadc83
ORCID 0009-0006-6665-9299
ParticipantIDs crossref_primary_10_1016_j_neucom_2025_131101
elsevier_sciencedirect_doi_10_1016_j_neucom_2025_131101
PublicationCentury 2000
PublicationDate 2025-11-01
2025-11-00
PublicationDateYYYYMMDD 2025-11-01
PublicationDate_xml – month: 11
  year: 2025
  text: 2025-11-01
  day: 01
PublicationDecade 2020
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Van der Maaten, Hinton (bib0185) 2008; 9
Fu, Nie, Wei, Zhang (bib0120) 2024; 63
Feng, Zhu, Ma (bib0085) 2024; 32
Kamal, Chandran, Supriya (bib0115) 2021; 24
Khalilabadi (bib0040) 2023; 8
Lian, Xu, Wan, Li (bib0025) 2017
Vaccaro (bib0010) 1998; 15
Mohammed, Hariharan, Kamal (bib0015) 2018; 2018
Dong, Fu, Zou, Zhao, Miao, Shen (bib0080) 2025; 318
Xie, Ren, Xu (bib0065) 2024; 249
He, Zhang, Ren, Sun (bib0190) 2016
Tian, Chen, Fu, Zhou (bib0125) 2023; 260
Santos-Domínguez, Torres-Guijarro, Cardenal-López, Pena-Gimenez (bib0170) 2016; 113
Gong, Chung, Glass (bib0145) 2021
Vaswani (bib0155) 2017
Khishe, Mohammadi (bib0045) 2019; 181
Zhao, Xie, Xu, Sun (bib0135) 2017; 38
Chen, Du, Quan, Zhou (bib0070) 2019; vol. 283
He, Chen, Xie, Li, Dollár, Girshick (bib0140) 2022
Xie, Xu, Ren, Li (bib0060) 2024; 156
Doan, Huynh-The, Kim (bib0095) 2020; 19
Chen, Liu, Li, Shen, Zhao (bib0055) 2022
Chen, Fan, Panda (bib0150) 2021
Oord, Li, Vinyals (bib0165) 2018
Hummel, van der Mei, Bhulai (bib0030) 2024; 298
Gong, Lai, Chung, Glass (bib0205) 2022; vol. 36
Liu, Shen, Luo, Zhao, Guo (bib0035) 2021; 178
Chen, Liu, Li, Shen, Zhao (bib0090) 2022
Xie, Ren, Xu (bib0130) 2022; 152
Simonyan (bib0195) 2014
Gazneli, Zimerman, Ridnik, Sharir, Noy (bib0160) 2022
Kuzin, Statsenko, Smirnova (bib0050) 2022
Smith, Rigby (bib0005) 2022; 266
Loshchilov (bib0175) 2017
Dosovitskiy (bib0200) 2020
Xiaoping, Jinsheng, Yuan (bib0110) 2021
Smith, Topin (bib0180) 2019; vol. 11006
Tong, Zhang, Ge (bib0020) 2020
Yang, Li, Shen, Xu (bib0100) 2019; 19
Xie, Ren, Xu (bib0075) 2022; 265
Shen, Yang, Li, Xu, Sheng (bib0105) 2018; 20
Van der Maaten (10.1016/j.neucom.2025.131101_bib0185) 2008; 9
Fu (10.1016/j.neucom.2025.131101_bib0120) 2024; 63
Loshchilov (10.1016/j.neucom.2025.131101_bib0175)
Chen (10.1016/j.neucom.2025.131101_bib0070) 2019; vol. 283
Chen (10.1016/j.neucom.2025.131101_bib0150) 2021
Shen (10.1016/j.neucom.2025.131101_bib0105) 2018; 20
Chen (10.1016/j.neucom.2025.131101_bib0090) 2022
Tian (10.1016/j.neucom.2025.131101_bib0125) 2023; 260
Gazneli (10.1016/j.neucom.2025.131101_bib0160)
Zhao (10.1016/j.neucom.2025.131101_bib0135) 2017; 38
Chen (10.1016/j.neucom.2025.131101_bib0055) 2022
Mohammed (10.1016/j.neucom.2025.131101_bib0015) 2018; 2018
Kamal (10.1016/j.neucom.2025.131101_bib0115) 2021; 24
Feng (10.1016/j.neucom.2025.131101_bib0085) 2024; 32
He (10.1016/j.neucom.2025.131101_bib0140) 2022
Xiaoping (10.1016/j.neucom.2025.131101_bib0110) 2021
Doan (10.1016/j.neucom.2025.131101_bib0095) 2020; 19
Vaccaro (10.1016/j.neucom.2025.131101_bib0010) 1998; 15
Simonyan (10.1016/j.neucom.2025.131101_bib0195)
Oord (10.1016/j.neucom.2025.131101_bib0165)
Khalilabadi (10.1016/j.neucom.2025.131101_bib0040) 2023; 8
Xie (10.1016/j.neucom.2025.131101_bib0130) 2022; 152
Gong (10.1016/j.neucom.2025.131101_bib0145)
Xie (10.1016/j.neucom.2025.131101_bib0075) 2022; 265
Liu (10.1016/j.neucom.2025.131101_bib0035) 2021; 178
Dong (10.1016/j.neucom.2025.131101_bib0080) 2025; 318
Vaswani (10.1016/j.neucom.2025.131101_bib0155) 2017
He (10.1016/j.neucom.2025.131101_bib0190) 2016
Lian (10.1016/j.neucom.2025.131101_bib0025) 2017
Yang (10.1016/j.neucom.2025.131101_bib0100) 2019; 19
Smith (10.1016/j.neucom.2025.131101_bib0005) 2022; 266
Gong (10.1016/j.neucom.2025.131101_bib0205) 2022; vol. 36
Xie (10.1016/j.neucom.2025.131101_bib0060) 2024; 156
Smith (10.1016/j.neucom.2025.131101_bib0180) 2019; vol. 11006
Kuzin (10.1016/j.neucom.2025.131101_bib0050) 2022
Tong (10.1016/j.neucom.2025.131101_bib0020) 2020
Xie (10.1016/j.neucom.2025.131101_bib0065) 2024; 249
Santos-Domínguez (10.1016/j.neucom.2025.131101_bib0170) 2016; 113
Khishe (10.1016/j.neucom.2025.131101_bib0045) 2019; 181
Hummel (10.1016/j.neucom.2025.131101_bib0030) 2024; 298
Dosovitskiy (10.1016/j.neucom.2025.131101_bib0200)
References_xml – volume: 15
  start-page: 21
  year: 1998
  end-page: 51
  ident: bib0010
  article-title: The past, present, and the future of underwater acoustic signal processing
  publication-title: IEEE Signal Process. Mag.
– start-page: 357
  year: 2021
  end-page: 366
  ident: bib0150
  article-title: Crossvit: cross-attention multi-scale vision transformer for image classification
  publication-title: Proceedings of the IEEE/CVF international conference on computer vision
– year: 2017
  ident: bib0175
  article-title: Decoupled weight decay regularization
– volume: 19
  start-page: 1
  year: 2020
  end-page: 5
  ident: bib0095
  article-title: Underwater acoustic target classification based on dense convolutional neural network
  publication-title: IEEE Geosci. Remote Sens. Lett.
– volume: 152
  start-page: 2641
  year: 2022
  end-page: 2651
  ident: bib0130
  article-title: Underwater-art: expanding information perspectives with text templates for underwater acoustic target recognition
  publication-title: J. Acoustical Soc. Am.
– volume: 8
  start-page: 10
  year: 2023
  end-page: 15
  ident: bib0040
  article-title: Underwater ship-radiated acoustic noise recognition based on mel-spectrogram and convolutional neural network
  publication-title: Int. J. Coast. Offshore Environ. Eng. (Ijcoe)
– volume: 38
  start-page: 43
  year: 2017
  end-page: 54
  ident: bib0135
  article-title: Multi-view learning overview: recent progress and new challenges
  publication-title: Inf. Fusion
– volume: 181
  start-page: 98
  year: 2019
  end-page: 108
  ident: bib0045
  article-title: Passive sonar target classification using multi-layer perceptron trained by salp swarm algorithm
  publication-title: Ocean Eng.
– volume: 19
  start-page: 1104
  year: 2019
  ident: bib0100
  article-title: A deep convolutional neural network inspired by auditory perception for underwater acoustic target recognition
  publication-title: Sensors
– year: 2014
  ident: bib0195
  article-title: Very deep convolutional networks for large-scale image recognition
– start-page: 1
  year: 2020
  end-page: 4
  ident: bib0020
  article-title: Classification and recognition of underwater target based on mfcc feature extraction
  publication-title: 2020 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)
– volume: 260
  year: 2023
  ident: bib0125
  article-title: Joint learning model for underwater acoustic target recognition
  publication-title: Know Based Syst.
– volume: 265
  year: 2022
  ident: bib0075
  article-title: Adaptive ship-radiated noise recognition with learnable fine-grained wavelet transform
  publication-title: Ocean Eng.
– start-page: 23
  year: 2022
  end-page: 28
  ident: bib0090
  article-title: Underwater acoustic target classification with joint learning framework and data augmentation
  publication-title: 2022 5th International Conference on Artificial Intelligence and Big Data (ICAIBD)
– year: 2018
  ident: bib0165
  article-title: Representation learning with contrastive predictive coding
– volume: vol. 283
  year: 2019
  ident: bib0070
  article-title: Underwater target recognition method based on convolution residual network
  publication-title: MATEC Web of Conferences
– volume: 266
  year: 2022
  ident: bib0005
  article-title: Underwater radiated noise from marine vessels: a review of noise reduction methods and technology
  publication-title: Ocean Eng.
– year: 2021
  ident: bib0145
  article-title: Ast: audio spectrogram transformer
– volume: 9
  year: 2008
  ident: bib0185
  article-title: Visualizing data using t-sne.
  publication-title: J. Mach. Learn. Res.
– volume: 178
  year: 2021
  ident: bib0035
  article-title: Underwater target recognition using convolutional recurrent neural networks with 3-d mel-spectrogram and data augmentation
  publication-title: Appl. Acoust.
– volume: vol. 11006
  start-page: 369
  year: 2019
  end-page: 386
  ident: bib0180
  article-title: Super-convergence: very fast training of neural networks using large learning rates
  publication-title: Artificial intelligence and machine learning for multi-domain operations applications
– volume: 113
  start-page: 64
  year: 2016
  end-page: 69
  ident: bib0170
  article-title: Shipsear: An underwater vessel noise database
  publication-title: Appl. Acoust.
– volume: 156
  start-page: 299
  year: 2024
  end-page: 313
  ident: bib0060
  article-title: Adversarial multi-task underwater acoustic target recognition: toward robustness against various influential factors
  publication-title: J. Acoustical Soc. Am.
– volume: 298
  year: 2024
  ident: bib0030
  article-title: A survey on machine learning in ship radiated noise
  publication-title: Ocean Eng.
– volume: 24
  start-page: 860
  year: 2021
  end-page: 871
  ident: bib0115
  article-title: Passive sonar automated target classifier for shallow waters using end-to-end learnable deep convolutional lstms
  publication-title: Eng. Sci. Technol. Int. J.
– volume: 32
  start-page: 1365
  year: 2024
  end-page: 1379
  ident: bib0085
  article-title: Masking hierarchical tokens for underwater acoustic target recognition with self-supervised learning
  publication-title: IEEE/ACM Trans. Audio, Speech, Language Process.
– volume: 20
  start-page: 990
  year: 2018
  ident: bib0105
  article-title: Auditory inspired convolutional neural networks for ship type classification with raw hydrophone data
  publication-title: Entropy
– start-page: 23
  year: 2022
  end-page: 28
  ident: bib0055
  article-title: Underwater acoustic target classification with joint learning framework and data augmentation
  publication-title: 2022 5th International Conference on Artificial Intelligence and Big Data (ICAIBD)
– volume: 318
  year: 2025
  ident: bib0080
  article-title: Caf-vit: a cross-attention based transformer network for underwater acoustic target recognition
  publication-title: Ocean Eng.
– start-page: 258
  year: 2017
  end-page: 262
  ident: bib0025
  article-title: Underwater acoustic target classification based on modified gfcc features
  publication-title: 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
– volume: 249
  year: 2024
  ident: bib0065
  article-title: Unraveling complex data diversity in underwater acoustic target recognition through convolution-based mixture of experts
  publication-title: Expert Syst. Appl.
– volume: 2018
  year: 2018
  ident: bib0015
  article-title: A gtcc-based underwater hmm target classifier with fading channel compensation
  publication-title: J. Sens.
– start-page: 770
  year: 2016
  end-page: 778
  ident: bib0190
  article-title: Deep residual learning for image recognition
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 16000
  year: 2022
  end-page: 16009
  ident: bib0140
  article-title: Masked autoencoders are scalable vision learners
  publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
– year: 2017
  ident: bib0155
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: vol. 36
  start-page: 10699
  year: 2022
  end-page: 10709
  ident: bib0205
  article-title: Ssast: self-supervised audio spectrogram transformer
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– year: 2020
  ident: bib0200
  article-title: An image is worth 16x16 words: transformers for image recognition at scale
– start-page: 87
  year: 2022
  end-page: 90
  ident: bib0050
  article-title: Automated sea vehicle classification system based on neural network
  publication-title: 2022 International Conference on Ocean Studies (ICOS)
– start-page: 1048
  year: 2021
  end-page: 1051
  ident: bib0110
  article-title: A new deep learning method for underwater target recognition based on one-dimensional time-domain signals
  publication-title: 2021 OES China Ocean Acoustics (COA)
– year: 2022
  ident: bib0160
  article-title: End-to-end audio strikes back: boosting augmentations towards an efficient audio classification network
– volume: 63
  start-page: 1
  year: 2024
  end-page: 14
  ident: bib0120
  article-title: Constructing a multi-modal based underwater acoustic target recognition method with a pre-trained language-audio model
  publication-title: IEEE Transactions On Geoscience And Remote Sensing
– start-page: 1
  year: 2020
  ident: 10.1016/j.neucom.2025.131101_bib0020
  article-title: Classification and recognition of underwater target based on mfcc feature extraction
– volume: 156
  start-page: 299
  issue: 1
  year: 2024
  ident: 10.1016/j.neucom.2025.131101_bib0060
  article-title: Adversarial multi-task underwater acoustic target recognition: toward robustness against various influential factors
  publication-title: J. Acoustical Soc. Am.
  doi: 10.1121/10.0026598
– volume: 265
  year: 2022
  ident: 10.1016/j.neucom.2025.131101_bib0075
  article-title: Adaptive ship-radiated noise recognition with learnable fine-grained wavelet transform
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2022.112626
– volume: 38
  start-page: 43
  year: 2017
  ident: 10.1016/j.neucom.2025.131101_bib0135
  article-title: Multi-view learning overview: recent progress and new challenges
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2017.02.007
– ident: 10.1016/j.neucom.2025.131101_bib0195
– ident: 10.1016/j.neucom.2025.131101_bib0200
– start-page: 87
  year: 2022
  ident: 10.1016/j.neucom.2025.131101_bib0050
  article-title: Automated sea vehicle classification system based on neural network
– start-page: 23
  year: 2022
  ident: 10.1016/j.neucom.2025.131101_bib0090
  article-title: Underwater acoustic target classification with joint learning framework and data augmentation
– ident: 10.1016/j.neucom.2025.131101_bib0175
– volume: 266
  year: 2022
  ident: 10.1016/j.neucom.2025.131101_bib0005
  article-title: Underwater radiated noise from marine vessels: a review of noise reduction methods and technology
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2022.112863
– ident: 10.1016/j.neucom.2025.131101_bib0160
– volume: 152
  start-page: 2641
  issue: 5
  year: 2022
  ident: 10.1016/j.neucom.2025.131101_bib0130
  article-title: Underwater-art: expanding information perspectives with text templates for underwater acoustic target recognition
  publication-title: J. Acoustical Soc. Am.
  doi: 10.1121/10.0015053
– start-page: 1048
  year: 2021
  ident: 10.1016/j.neucom.2025.131101_bib0110
  article-title: A new deep learning method for underwater target recognition based on one-dimensional time-domain signals
– volume: 2018
  year: 2018
  ident: 10.1016/j.neucom.2025.131101_bib0015
  article-title: A gtcc-based underwater hmm target classifier with fading channel compensation
  publication-title: J. Sens.
  doi: 10.1155/2018/6593037
– ident: 10.1016/j.neucom.2025.131101_bib0165
– volume: 8
  start-page: 10
  year: 2023
  ident: 10.1016/j.neucom.2025.131101_bib0040
  article-title: Underwater ship-radiated acoustic noise recognition based on mel-spectrogram and convolutional neural network
  publication-title: Int. J. Coast. Offshore Environ. Eng. (Ijcoe)
– volume: 9
  year: 2008
  ident: 10.1016/j.neucom.2025.131101_bib0185
  article-title: Visualizing data using t-sne.
  publication-title: J. Mach. Learn. Res.
– start-page: 770
  year: 2016
  ident: 10.1016/j.neucom.2025.131101_bib0190
  article-title: Deep residual learning for image recognition
– volume: 249
  year: 2024
  ident: 10.1016/j.neucom.2025.131101_bib0065
  article-title: Unraveling complex data diversity in underwater acoustic target recognition through convolution-based mixture of experts
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2024.123431
– volume: 19
  start-page: 1104
  issue: 5
  year: 2019
  ident: 10.1016/j.neucom.2025.131101_bib0100
  article-title: A deep convolutional neural network inspired by auditory perception for underwater acoustic target recognition
  publication-title: Sensors
  doi: 10.3390/s19051104
– volume: 181
  start-page: 98
  year: 2019
  ident: 10.1016/j.neucom.2025.131101_bib0045
  article-title: Passive sonar target classification using multi-layer perceptron trained by salp swarm algorithm
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2019.04.013
– start-page: 258
  year: 2017
  ident: 10.1016/j.neucom.2025.131101_bib0025
  article-title: Underwater acoustic target classification based on modified gfcc features
– start-page: 357
  year: 2021
  ident: 10.1016/j.neucom.2025.131101_bib0150
  article-title: Crossvit: cross-attention multi-scale vision transformer for image classification
– volume: vol. 283
  year: 2019
  ident: 10.1016/j.neucom.2025.131101_bib0070
  article-title: Underwater target recognition method based on convolution residual network
– year: 2017
  ident: 10.1016/j.neucom.2025.131101_bib0155
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 20
  start-page: 990
  issue: 12
  year: 2018
  ident: 10.1016/j.neucom.2025.131101_bib0105
  article-title: Auditory inspired convolutional neural networks for ship type classification with raw hydrophone data
  publication-title: Entropy
  doi: 10.3390/e20120990
– volume: 298
  year: 2024
  ident: 10.1016/j.neucom.2025.131101_bib0030
  article-title: A survey on machine learning in ship radiated noise
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2024.117252
– start-page: 23
  year: 2022
  ident: 10.1016/j.neucom.2025.131101_bib0055
  article-title: Underwater acoustic target classification with joint learning framework and data augmentation
– volume: 32
  start-page: 1365
  year: 2024
  ident: 10.1016/j.neucom.2025.131101_bib0085
  article-title: Masking hierarchical tokens for underwater acoustic target recognition with self-supervised learning
  publication-title: IEEE/ACM Trans. Audio, Speech, Language Process.
  doi: 10.1109/TASLP.2024.3358719
– volume: 113
  start-page: 64
  year: 2016
  ident: 10.1016/j.neucom.2025.131101_bib0170
  article-title: Shipsear: An underwater vessel noise database
  publication-title: Appl. Acoust.
  doi: 10.1016/j.apacoust.2016.06.008
– volume: 63
  start-page: 1
  year: 2024
  ident: 10.1016/j.neucom.2025.131101_bib0120
  article-title: Constructing a multi-modal based underwater acoustic target recognition method with a pre-trained language-audio model
  publication-title: IEEE Transactions On Geoscience And Remote Sensing
– volume: 318
  year: 2025
  ident: 10.1016/j.neucom.2025.131101_bib0080
  article-title: Caf-vit: a cross-attention based transformer network for underwater acoustic target recognition
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2024.120049
– volume: 15
  start-page: 21
  issue: 4
  year: 1998
  ident: 10.1016/j.neucom.2025.131101_bib0010
  article-title: The past, present, and the future of underwater acoustic signal processing
  publication-title: IEEE Signal Process. Mag.
  doi: 10.1109/79.689583
– start-page: 16000
  year: 2022
  ident: 10.1016/j.neucom.2025.131101_bib0140
  article-title: Masked autoencoders are scalable vision learners
– volume: 178
  year: 2021
  ident: 10.1016/j.neucom.2025.131101_bib0035
  article-title: Underwater target recognition using convolutional recurrent neural networks with 3-d mel-spectrogram and data augmentation
  publication-title: Appl. Acoust.
  doi: 10.1016/j.apacoust.2021.107989
– volume: 24
  start-page: 860
  issue: 4
  year: 2021
  ident: 10.1016/j.neucom.2025.131101_bib0115
  article-title: Passive sonar automated target classifier for shallow waters using end-to-end learnable deep convolutional lstms
  publication-title: Eng. Sci. Technol. Int. J.
– volume: vol. 36
  start-page: 10699
  year: 2022
  ident: 10.1016/j.neucom.2025.131101_bib0205
  article-title: Ssast: self-supervised audio spectrogram transformer
– volume: 19
  start-page: 1
  year: 2020
  ident: 10.1016/j.neucom.2025.131101_bib0095
  article-title: Underwater acoustic target classification based on dense convolutional neural network
  publication-title: IEEE Geosci. Remote Sens. Lett.
  doi: 10.1109/LGRS.2020.3029584
– ident: 10.1016/j.neucom.2025.131101_bib0145
– volume: 260
  year: 2023
  ident: 10.1016/j.neucom.2025.131101_bib0125
  article-title: Joint learning model for underwater acoustic target recognition
  publication-title: Know Based Syst.
  doi: 10.1016/j.knosys.2022.110119
– volume: vol. 11006
  start-page: 369
  year: 2019
  ident: 10.1016/j.neucom.2025.131101_bib0180
  article-title: Super-convergence: very fast training of neural networks using large learning rates
SSID ssj0017129
Score 2.4562037
Snippet Underwater acoustic target recognition is crucial for marine exploration and environmental monitoring. However, the redundancy in raw time-domain signals and...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 131101
SubjectTerms Contrastive learning
Cross-attention mechanism
Dual-stage learning
Masked autoencoder
Underwater acoustic target recognition
Title Dual-stage learning framework for underwater acoustic target recognition with cross-attention mechanism and audio-guided contrastive learning
URI https://dx.doi.org/10.1016/j.neucom.2025.131101
Volume 652
WOSCitedRecordID wos001543233800012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0925-2312
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0017129
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWlgMX3qjlJR-4rVzl4cTxcQVFgKoKiSKtuER-ZZuqTartprQ_An4z49jOpixCgMQlSqzEs9rvkz2ZfDOD0CuRGNjFTE60hDcdaqKU8IJKUnGquUlimUWybzbBDg-L-Zx_nEy-h1yYy1PWNMXVFT__r1DDGIBtU2f_Au5hUhiAcwAdjgA7HP8I-DedOCXg8y1MaAmxmFZBgtWrCm3e2PKrsOURYT3s23lNnSJ8OuiJ2sar0u0uSmwRTieLPDM2VTh01hCdrluy6GpttFO9i4teixQsj33fvg6I6rtI-PjE7MyWadCWk0M84suxaJ3ku1lci3YQDNVd72cbP-fozoPrrhLr4QOfOl8fd_U4ppFkPrlvCLRtJNu4iCXcCO7ojcU7d_VvNzYCF5M42WtMZ1VB1sierSzkrdwssf3JTm1nBn8wZiylt9B2wjIOC_327P3-_MPwXYrFiave6H9KSMbsFYObtn7t7IwcmKP76K5_88Azx5gHaGKah-he6OqB_SL_CH1bEwgHGPFAIAwEwmsC4UAg7AiERwTClkD4JwLhgUAYCITHBMIjAg2WH6PPb_ePXr8jvmkHUbD6r0ilaV7JOGNRonSRSF4xplgmmNDUxJWMKqVNoSgTQnIluMyYoGkhNYcrrYr0Cdpq2sbsIBxV4CvFsWDG9o3UQhSUqiit4jjPTZqoXUTCv1ueu9osZRAtnpQOjdKiUTo0dhELEJTev3R-Ywms-e2TT__5yWfozprgz9HWatmZF-i2ulzVF8uXnl4_ACzWq2Q
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Dual-stage+learning+framework+for+underwater+acoustic+target+recognition+with+cross-attention+mechanism+and+audio-guided+contrastive+learning&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Zhao%2C+Rongyao&rft.au=Liu%2C+Feng&rft.au=Zhao%2C+Lyufang&rft.au=Li%2C+Daihui&rft.date=2025-11-01&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.volume=652&rft_id=info:doi/10.1016%2Fj.neucom.2025.131101&rft.externalDocID=S0925231225017734
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon