{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:49:10Z","timestamp":1776876550752,"version":"3.51.2"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.asoc.2026.115083","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T17:22:51Z","timestamp":1774545771000},"page":"115083","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["H-Net: A transformer based multistage fusion convolutional neural network for underwater object detection in complex environments"],"prefix":"10.1016","volume":"197","author":[{"given":"Ashish","family":"Kumar","sequence":"first","affiliation":[]},{"given":"Shikha","family":"Bhalla","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115083_bib1","series-title":"Intelligence Enabled Research: DoSIER. 2021","first-page":"91","article-title":"A survey on underwater object detection","author":"Sarkar","year":"2022"},{"key":"10.1016\/j.asoc.2026.115083_bib2","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2019.112870","article-title":"Rotated object detection with forward-looking sonar in underwater applications","volume":"140","author":"Neves","year":"2020","journal-title":"Expert Syst. Appl."},{"issue":"15","key":"10.1016\/j.asoc.2026.115083_bib3","doi-asserted-by":"crossref","first-page":"20871","DOI":"10.1007\/s11042-022-12502-1","article-title":"Underwater object detection: architectures and algorithms\u2013a comprehensive review","volume":"81","author":"Fayaz","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.asoc.2026.115083_bib4","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2020.104458","article-title":"Review on deep learning techniques for marine object recognition: architectures and algorithms","volume":"118","author":"Wang","year":"2022","journal-title":"Control Eng. Pract."},{"key":"10.1016\/j.asoc.2026.115083_bib5","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1007\/s11760-020-01818-w","article-title":"Multi-scale ResNet for real-time underwater object detection","volume":"15","author":"Pan","year":"2021","journal-title":"Signal Image Video Process."},{"issue":"3","key":"10.1016\/j.asoc.2026.115083_bib6","doi-asserted-by":"crossref","first-page":"1592","DOI":"10.1109\/JSEN.2019.2946587","article-title":"AUV-based multi-view scanning method for 3-D reconstruction of underwater object using forward scan sonar","volume":"20","author":"Kim","year":"2019","journal-title":"IEEE Sens. J."},{"issue":"3","key":"10.1016\/j.asoc.2026.115083_bib7","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1007\/s12555-019-0691-3","article-title":"Realistic sonar image simulation using deep learning for underwater object detection","volume":"18","author":"Sung","year":"2020","journal-title":"Int. J. Control Autom. Syst."},{"key":"10.1016\/j.asoc.2026.115083_bib8","series-title":"In2020 IEEE International Conference on Image Processing (ICIP)","first-page":"1971","article-title":"Towards domain generalization in underwater object detection","author":"Liu","year":"2020"},{"key":"10.1016\/j.asoc.2026.115083_bib9","unstructured":"Chen L., Tong L., Zhou F., Jiang Z., Li Z., Lv J., Dong J., Zhou H. (2020) A benchmark dataset for both underwater image enhancement and underwater object detection. arXiv preprint arXiv:2006.15789."},{"key":"10.1016\/j.asoc.2026.115083_bib10","series-title":"2021 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.asoc.2026.115083_bib11","series-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"2588","article-title":"Roimix: proposal-fusion among multiple images for underwater object detection","author":"Lin","year":"2020"},{"key":"10.1016\/j.asoc.2026.115083_bib12","series-title":"2019 IEEE International Symposium on Technologies for Homeland Security (HST)","first-page":"1","article-title":"Underwater object tracking benchmark and dataset","author":"Kezebou","year":"2019"},{"key":"10.1016\/j.asoc.2026.115083_bib13","series-title":"2020 chinese automation congress (CAC)","first-page":"5928","article-title":"Research on the correlation between image enhancement and underwater object detection","author":"Zhang","year":"2020"},{"key":"10.1016\/j.asoc.2026.115083_bib14","doi-asserted-by":"crossref","first-page":"5413","DOI":"10.1007\/s10462-021-10025-z","article-title":"Underwater image enhancement: a comprehensive review, recent trends, challenges and applications","volume":"54","author":"Raveendran","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.asoc.2026.115083_bib15","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2019.100204","article-title":"Background subtraction in real applications: Challenges, current models and future directions","volume":"35","author":"Garcia-Garcia","year":"2020","journal-title":"Comput. Sci. Rev."},{"key":"10.1016\/j.asoc.2026.115083_bib16","unstructured":"Chen L., Zhou F., Wang S., Dong J., Li N., Ma H., Wang X., Zhou H. (2020) SWIPENET: Object detection in noisy underwater images. arXiv preprint arXiv:2010.10006."},{"key":"10.1016\/j.asoc.2026.115083_bib17","doi-asserted-by":"crossref","first-page":"47407","DOI":"10.1109\/ACCESS.2020.2978880","article-title":"Underwater object classification in sidescan sonar images using deep transfer learning and semisynthetic training data","volume":"8","author":"Huo","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2026.115083_bib18","series-title":"2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems (iCACCESS)","first-page":"1","article-title":"Under Water Objects Detection and Classification using Deep Learning Technique","author":"Roy","year":"2024"},{"issue":"1","key":"10.1016\/j.asoc.2026.115083_bib19","doi-asserted-by":"crossref","DOI":"10.1080\/08839514.2022.2146853","article-title":"Deep learning approach for objects detection in underwater pipeline images","volume":"36","author":"Ga\u0161parovi\u0107","year":"2022","journal-title":"Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115083_bib20","series-title":"2022 5th International Conference on Intelligent Autonomous Systems (ICoIAS)","first-page":"37","article-title":"Underwater object detection based on improved SSD with convolutional block attention","author":"Li","year":"2022"},{"key":"10.1016\/j.asoc.2026.115083_bib21","first-page":"1","article-title":"Underwater object classification and detection: first results and open challenges","author":"Jesus","year":"2022","journal-title":"Oceans"},{"key":"10.1016\/j.asoc.2026.115083_bib22","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3534098","article-title":"Advancing underwater vision: a survey of deep learning models for underwater object recognition and tracking","author":"Elmezain","year":"2025","journal-title":"IEEE Access"},{"issue":"19","key":"10.1016\/j.asoc.2026.115083_bib23","doi-asserted-by":"crossref","first-page":"20339","DOI":"10.1007\/s11042-024-19782-9","article-title":"Analysis of recent techniques in marine object detection: a review","volume":"84","author":"Bhalla","year":"2025","journal-title":"Multimed. Tools Appl."},{"issue":"6","key":"10.1016\/j.asoc.2026.115083_bib24","doi-asserted-by":"crossref","first-page":"5923","DOI":"10.1007\/s12145-024-01473-6","article-title":"Feature-adaptive FPN with multiscale context integration for underwater object detection","volume":"17","author":"Bhalla","year":"2024","journal-title":"Earth Sci. Inform."},{"issue":"6","key":"10.1016\/j.asoc.2026.115083_bib25","first-page":"556","article-title":"HydR-CNN: advancing underwater object detection using a multi-stage framework with hybrid R-CNN and pyramid vision transformer with augmented convolution","volume":"140","author":"Bhalla","year":"2025","journal-title":"Eur. Phys. J."},{"key":"10.1016\/j.asoc.2026.115083_bib26","first-page":"1","article-title":"A novel underwater marine dataset with diverse scenarios for robust object detection","author":"Bhalla","year":"2024","journal-title":"Proc. 2024 Sixt. Int. Conf. Contemp. Comput."},{"key":"10.1016\/j.asoc.2026.115083_bib27","series-title":"International Conference on Innovative Computing and Communication","first-page":"257","article-title":"Evaluation of Deep Learning-Based Underwater Object Detection Algorithms","author":"Bhalla","year":"2025"},{"key":"10.1016\/j.asoc.2026.115083_bib28","series-title":"Artificial Intelligence and Sustainable Innovation","first-page":"341","article-title":"Underwater image enhancement and object detection using vision transformers","author":"Bhalla","year":"2026"},{"key":"10.1016\/j.asoc.2026.115083_bib29","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102562","article-title":"Correlation filter based single object tracking: A review","volume":"112","author":"Kumar","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.asoc.2026.115083_bib30","series-title":"Visual object tracking using deep learning","author":"Kumar","year":"2023"},{"key":"10.1016\/j.asoc.2026.115083_bib31","series-title":"Object Tracking Technology: Trends, Challenges and Applications","first-page":"183","article-title":"Deep learning-based multi-object tracking","author":"Kumar","year":"2023"},{"issue":"9","key":"10.1016\/j.asoc.2026.115083_bib32","doi-asserted-by":"crossref","first-page":"10651","DOI":"10.1007\/s10462-023-10438-y","article-title":"An efficient lightweight convolutional neural network for industrial surface defect detection","volume":"56","author":"Zhang","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.asoc.2026.115083_bib33","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-025-11439-9","article-title":"Reinforcement learning for single-agent to multi-agent systems: from basic theory to industrial application progress, a survey","author":"Zhang","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.asoc.2026.115083_bib34","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112243","article-title":"Reinforcement learning-based secure tracking control for nonlinear interconnected systems: an event-triggered solution approach","volume":"161","author":"Qin","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115083_bib35","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113466","article-title":"Unsupervised image stitching based on Generative Adversarial Networks and feature frequency awareness algorithm","author":"Qin","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115083_bib36","doi-asserted-by":"crossref","first-page":"117235","DOI":"10.1109\/ACCESS.2022.3219592","article-title":"Two-stage underwater object detection network using swin transformer","volume":"10","author":"Liu","year":"2022","journal-title":"IEEE Access"},{"issue":"13","key":"10.1016\/j.asoc.2026.115083_bib37","doi-asserted-by":"crossref","first-page":"3841","DOI":"10.1049\/ipr2.12901","article-title":"Cformer: an underwater image enhancement hybrid network combining convolution and transformer","volume":"17","author":"Deng","year":"2023","journal-title":"IET Image Process."},{"key":"10.1016\/j.asoc.2026.115083_bib38","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2023.3271644","article-title":"Learning heavily-degraded prior for underwater object detection","author":"Fu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.asoc.2026.115083_bib39","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1049\/cvi2.12161","article-title":"A multi-scale feature representation and interaction network for underwater object detection","volume":"17","author":"Yuan","year":"2023","journal-title":"IET Comput. Vis."},{"key":"10.1016\/j.asoc.2026.115083_bib40","article-title":"Edge-guided representation learning for underwater object detection","author":"Dai","year":"2023","journal-title":"CAAI Trans. Intell. Technol."},{"key":"10.1016\/j.asoc.2026.115083_bib41","doi-asserted-by":"crossref","unstructured":"Saoud L.S., Seneviratne L., Hussain I. (2023) MARS: Multi-Scale Adaptive Robotics Vision for Underwater Object Detection and Domain Generalization. arXiv preprint arXiv:2312.15275.","DOI":"10.1109\/ICIP51287.2024.10647684"},{"key":"10.1016\/j.asoc.2026.115083_bib42","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110435","article-title":"Unit module: a lightweight joint image enhancement module for underwater object detection","volume":"151","author":"Liu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.asoc.2026.115083_bib43","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."},{"key":"10.1016\/j.asoc.2026.115083_bib44","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2023.102401","article-title":"YWnet: a convolutional block attention-based fusion deep learning method for complex underwater small target detection","volume":"79","author":"Liu","year":"2024","journal-title":"Ecol. Inform."},{"key":"10.1016\/j.asoc.2026.115083_bib45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/17445302.2025.2539946","article-title":"Hybrid deep learning based vanished object detection and tracking in underwater image processing","author":"Rajkamal","year":"2025","journal-title":"Ships Offshore Struct."},{"key":"10.1016\/j.asoc.2026.115083_bib46","article-title":"A lightweight network enhanced by attention-guided cross-scale interaction for underwater object detection","author":"Zhang","year":"2025","journal-title":"Appl. Soft Comput."},{"issue":"2","key":"10.1016\/j.asoc.2026.115083_bib47","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1007\/s11554-025-01674-2","article-title":"Hcl-yolo: a lightweight and efficient underwater object detection algorithm","volume":"22","author":"Liang","year":"2025","journal-title":"J. Real. Time Image Process."},{"key":"10.1016\/j.asoc.2026.115083_bib48","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3556203","article-title":"ERD: encoder-residual-decoder neural network for underwater image enhancement","author":"Cao","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.asoc.2026.115083_bib49","article-title":"U-SAS: U-shape network with multi-level enhancement and global decoding for synthetic aperture sonar image semantic segmentation","author":"Li","year":"2024","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.asoc.2026.115083_bib50","article-title":"MFSonar: multiscale frequency domain contextual denoising for forward-looking sonar image semantic segmentation","author":"Li","year":"2025","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.asoc.2026.115083_bib51","article-title":"Fine-tuning SAM for forward-looking sonar with collaborative prompts and embedding","author":"Li","year":"2025","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.asoc.2026.115083_bib52","first-page":"1","article-title":"MSFRNet: multiscale feature recomposition network for singleimage dehazing","author":"Pushpalatha","year":"2025","journal-title":"Circuits Syst. Signal Process."},{"key":"10.1016\/j.asoc.2026.115083_bib53","doi-asserted-by":"crossref","unstructured":"Lin T.Y., Goyal P., Girshick R., He K., Dollar P. (2017) \u201cFocal loss for dense object detection,\u201d pp. 2999\u20133007.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.asoc.2026.115083_bib54","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.asoc.2026.115083_bib55","unstructured":"\u3008https:\/\/universe.roboflow.com\/srm-nmbuq\/urpc\/dataset\/1\u3009."},{"key":"10.1016\/j.asoc.2026.115083_bib56","unstructured":"\u3008https:\/\/github.com\/mousecpn\/Collection-of-Underwater-Object-Detection-Dataset?tab=readme-ov-file\u3009."},{"key":"10.1016\/j.asoc.2026.115083_bib57","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.neucom.2023.01.053","article-title":"Achieving domain generalization for underwater object detection by domain mixup and contrastive learning","volume":"528","author":"Chen","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115083_bib58","series-title":"2018 IEEE\/ACM 26th international symposium on quality of service (IWQoS)","first-page":"1","article-title":"Improved adam optimizer for deep neural networks","author":"Zhang","year":"2018"},{"key":"10.1016\/j.asoc.2026.115083_bib59","unstructured":"Birkl R., Wofk D., M\u00fcller M. (2023) Midas v3. 1--a model zoo for robust monocular relative depth estimation. arXiv preprint arXiv:2307.14460."},{"key":"10.1016\/j.asoc.2026.115083_bib60","unstructured":"Y. Chen, T. Yang, X. Zhang, G. Meng, C. Pan, J. Sun, 2019, Detnas: Neural architecture search on object detection,\u201d CoRR, vol. abs\/1903.10979, [Online]. Available: http:\/\/arxiv.org\/abs\/1903.10979."},{"key":"10.1016\/j.asoc.2026.115083_bib61","doi-asserted-by":"crossref","unstructured":"J. Cao, H. Cholakkal, R.M. Anwer, F.S. Khan, Y. Pang, L. Shao, 2020, D2det: Towards high quality object detection and instance segmentation, in: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11482\u201311491.","DOI":"10.1109\/CVPR42600.2020.01150"},{"key":"10.1016\/j.asoc.2026.115083_bib62","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, 2020, Deformable detr: Deformable transformers for end-to-end object detection, in: International Conference on Learning Representations."},{"key":"10.1016\/j.asoc.2026.115083_bib63","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, 2021, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005314?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005314?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:08:28Z","timestamp":1776874108000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626005314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":63,"alternative-id":["S1568494626005314"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115083","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"H-Net: A transformer based multistage fusion convolutional neural network for underwater object detection in complex environments","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115083","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":"115083"}}