{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:13:24Z","timestamp":1784200404497,"version":"3.55.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515110420"],"award-info":[{"award-number":["2022A1515110420"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","award":["RCBS20221008093227028"],"award-info":[{"award-number":["RCBS20221008093227028"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No.12405214"],"award-info":[{"award-number":["Grant No.12405214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s10489-024-05971-4","type":"journal-article","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T10:44:40Z","timestamp":1734086680000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Multi-scale feature map fusion encoding for underwater object segmentation"],"prefix":"10.1007","volume":"55","author":[{"given":"Chengxiang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoxin","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhui","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyuan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubin","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7073-171X","authenticated-orcid":false,"given":"Anqi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,13]]},"reference":[{"key":"5971_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2024.117911","volume":"305","author":"L Hong","year":"2024","unstructured":"Hong L, Wang X, Zhang D (2024) Cfd-based hydrodynamic performance investigation of autonomous underwater vehicles: A survey. Ocean Eng 305:117911","journal-title":"Ocean Eng"},{"key":"5971_CR2","doi-asserted-by":"crossref","unstructured":"Osayi Philip Igbinenikaro OOA, Etukudoh EA (2024) A comparative review of subsea navigation technologies in offshore engineering projects. Int J Front Eng Technol Res 6(2):019\u2013034","DOI":"10.53294\/ijfetr.2024.6.2.0031"},{"key":"5971_CR3","doi-asserted-by":"publisher","first-page":"46202","DOI":"10.1109\/ACCESS.2024.3380458","volume":"12","author":"K Hasan","year":"2024","unstructured":"Hasan K, Ahmad S, Liaf AF, Karimi M, Ahmed T, Shawon MA, Mekhilef S (2024) Oceanic challenges to technological solutions: A review of autonomous underwater vehicle path technologies in biomimicry, control, navigation, and sensing. IEEE Access 12:46202\u201346231","journal-title":"IEEE Access"},{"key":"5971_CR4","doi-asserted-by":"crossref","unstructured":"Huy DQ, Sadjoli N, Azam AB, Elhadidi B, Cai Y, Seet G (2023) Object perception in underwater environments: A survey on sensors and sensing methodologies. Ocean Eng 267","DOI":"10.1016\/j.oceaneng.2022.113202"},{"key":"5971_CR5","doi-asserted-by":"crossref","unstructured":"Li M, Zhang H, Gruen A, Li D (2024) A survey on underwater coral image segmentation based on deep learning. Geo-spatial Inf Sci p 1\u201325","DOI":"10.1080\/10095020.2024.2343323"},{"key":"5971_CR6","first-page":"1","volume":"2022","author":"M Pergeorelis","year":"2022","unstructured":"Pergeorelis M, Bazik M, Saponaro P, Kim J, Kambhamettu C (2022) Synthetic data for semantic segmentation in underwater imagery. in OCEANS. Hampton Roads. IEEE 2022:1\u20136","journal-title":"Hampton Roads. IEEE"},{"key":"5971_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127599","volume":"583","author":"L Ji","year":"2024","unstructured":"Ji L, Du Y, Dang Y, Gao W, Zhang H (2024) A survey of methods for addressing the challenges of referring image segmentation. Neurocomputing 583:127599","journal-title":"Neurocomputing"},{"key":"5971_CR8","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1016\/j.neucom.2022.01.005","volume":"493","author":"Y Mo","year":"2022","unstructured":"Mo Y, Wu Y, Yang X, Liu F, Liao Y (2022) Review the state-of-the-art technologies of semantic segmentation based on deep learning. Neurocomputing 493:626\u2013646","journal-title":"Neurocomputing"},{"key":"5971_CR9","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.neucom.2019.11.118","volume":"406","author":"S Hao","year":"2020","unstructured":"Hao S, Zhou Y, Guo Y (2020) A brief survey on semantic segmentation with deep learning. Neurocomputing 406:302\u2013321","journal-title":"Neurocomputing"},{"key":"5971_CR10","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation.\u2019 in Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"5971_CR11","first-page":"234","volume":"2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. in Medical Image Computing and Computer-Assisted Intervention-MICCAI, 18th International Conference, Munich, Germany, October 5\u20139, Proceedings, Part III 18. Springer 2015:234\u2013241","journal-title":"Springer"},{"key":"5971_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106210","volume":"207","author":"J Wang","year":"2021","unstructured":"Wang J, Liu X (2021) Medical image recognition and segmentation of pathological slices of gastric cancer based on deeplab v3+ neural network. Comput Methods Prog Biomed 207:106210","journal-title":"Comput Methods Prog Biomed"},{"issue":"4","key":"5971_CR13","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2017","unstructured":"Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Patt Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"5971_CR14","doi-asserted-by":"crossref","unstructured":"Bai Z, Jing J (2023) Mobile-deeplab: a lightweight pixel segmentation-based method for fabric defect detection. J Intell Manuf","DOI":"10.1007\/s10845-023-02205-1"},{"key":"5971_CR15","doi-asserted-by":"crossref","unstructured":"Chen L, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. in Proceedings of the European conference on computer vision (ECCV), pp 801\u2013818","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"5971_CR16","doi-asserted-by":"publisher","first-page":"3603","DOI":"10.1109\/TMM.2020.3028482","volume":"23","author":"P Zhuang","year":"2021","unstructured":"Zhuang P, Wang Y, Qiao Y (2021) Wildfish++: A comprehensive fish benchmark for multimedia research. IEEE Trans Multimed 23:3603\u20133617","journal-title":"IEEE Trans Multimed"},{"key":"5971_CR17","doi-asserted-by":"crossref","unstructured":"Ditria EM, Connolly RM, Jinks EL, Lopez-Marcano S (2021) Annotated video footage for automated identification and counting of fish in unconstrained seagrass habitats. Front Marine Sci 8","DOI":"10.3389\/fmars.2021.629485"},{"key":"5971_CR18","doi-asserted-by":"crossref","unstructured":"Cai L, Chen C, Chai H (2021) Underwater distortion target recognition network (udtrnet) via enhanced image features. Comput Intell Neurosci 2021:1\u201310","DOI":"10.1155\/2021\/4193625"},{"key":"5971_CR19","doi-asserted-by":"crossref","unstructured":"Zhang P, Yu H, Li H, Zhang X, Wei S, Tu W, Yang Z, Wu J, Lin Y (2023) Msgnet: multi-source guidance network for fish segmentation in underwater videos. Front Marine Sci 10","DOI":"10.3389\/fmars.2023.1256594"},{"issue":"2018","key":"5971_CR20","doi-asserted-by":"publisher","first-page":"60956","DOI":"10.1109\/ACCESS.2018.2875412","volume":"6","author":"M Martin-Abadal","year":"2018","unstructured":"Martin-Abadal M, Guerrero-Font E, Bonin-Font F, Gonzalez-Cid Y (2018) Deep semantic segmentation in an auv for online posidonia oceanica meadows identification. IEEE Access 6(2018):60956\u201360967","journal-title":"IEEE Access"},{"key":"5971_CR21","doi-asserted-by":"crossref","unstructured":"Islam MJ, Edge C, Xiao Y, Luo P, Mehtaz M, Morse C, Enan SS, Sattar J (2020) Semantic segmentation of underwater imagery: Dataset and benchmark. in 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp 1769\u20131776","DOI":"10.1109\/IROS45743.2020.9340821"},{"key":"5971_CR22","doi-asserted-by":"crossref","unstructured":"Nezla N, Haridas TM, Supriya M (2021) Semantic segmentation of underwater images using unet architecture based deep convolutional encoder decoder model. in 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), vol 1. IEEE, pp 28\u201333","DOI":"10.1109\/ICACCS51430.2021.9441804"},{"issue":"3","key":"5971_CR23","doi-asserted-by":"publisher","first-page":"3594","DOI":"10.1007\/s10489-022-03767-y","volume":"53","author":"J Zhou","year":"2023","unstructured":"Zhou J, Yang T, Zhang W (2023) Underwater vision enhancement technologies: a comprehensive review, challenges, and recent trends. Appl Intell 53(3):3594\u20133621","journal-title":"Appl Intell"},{"key":"5971_CR24","doi-asserted-by":"crossref","unstructured":"Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5693\u20135703","DOI":"10.1109\/CVPR.2019.00584"},{"issue":"10","key":"5971_CR25","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang J, Sun K, Cheng T, Jiang B, Deng C, Zhao Y, Liu D, Mu Y, Tan M, Wang X et al (2020) Deep high-resolution representation learning for visual recognition. IEEE Trans Patt Anal Mach Intell 43(10):3349\u20133364","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"5971_CR26","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. in Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"5971_CR27","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V et al (2019) Searching for mobilenetv3. in Proceedings of the IEEE\/CVF international conference on computer vision, pp 1314\u20131324","DOI":"10.1109\/ICCV.2019.00140"},{"key":"5971_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. in Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"5971_CR29","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. in Proc of the AAAI Conf Artif Intell 31(1)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"5971_CR30","doi-asserted-by":"crossref","unstructured":"Rahnemoonfar M, Dobbs D (2019) Semantic segmentation of underwater sonar imagery with deep learning. in IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE, pp 9455\u20139458","DOI":"10.1109\/IGARSS.2019.8898742"},{"key":"5971_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127585","volume":"584","author":"HF Tolie","year":"2024","unstructured":"Tolie HF, Ren J, Elyan E (2024) Dicam: Deep inception and channel-wise attention modules for underwater image enhancement. Neurocomputing 584:127585","journal-title":"Neurocomputing"},{"issue":"3","key":"5971_CR32","doi-asserted-by":"publisher","first-page":"188","DOI":"10.3390\/jmse8030188","volume":"8","author":"F Liu","year":"2020","unstructured":"Liu F, Fang M (2020) Semantic segmentation of underwater images based on improved deeplab. J Marine Sci Eng 8(3):188","journal-title":"J Marine Sci Eng"},{"issue":"1","key":"5971_CR33","doi-asserted-by":"publisher","first-page":"69","DOI":"10.3390\/jmse11010069","volume":"11","author":"A Jin","year":"2023","unstructured":"Jin A, Zeng X (2023) A novel deep learning method for underwater target recognition based on res-dense convolutional neural network with attention mechanism. J Marine Sci Eng 11(1):69","journal-title":"J Marine Sci Eng"},{"key":"5971_CR34","doi-asserted-by":"crossref","unstructured":"Ding X, Zhang X, Ma N, Han J, Ding G, Sun J (2021) Repvgg: Making vgg-style convnets great again. in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13733\u201313742","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"5971_CR35","doi-asserted-by":"crossref","unstructured":"Lian S, Li H, Cong R, Li S, Zhang W, Kwong S (2023) Watermask: Instance segmentation for underwater imagery. in 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE","DOI":"10.1109\/ICCV51070.2023.00126"},{"key":"5971_CR36","unstructured":"Hong J, Fulton M, Sattar J (2020) Trashcan: A semantically-segmented dataset towards visual detection of marine debris. arXiv:2007.08097"},{"issue":"11","key":"5971_CR37","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu C, Gao C, Wang J, Yu G, Shen C, Sang N (2021) Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. Int J Comput Vis 129(11):3051\u20133068","journal-title":"Int J Comput Vis"},{"key":"5971_CR38","unstructured":"Peng J, Liu Y, Tang S, Hao Y, Chu L, Chen G, Wu Z, Chen Z, Yu Z, Du Y et al (2022) Pp-liteseg: A superior real-time semantic segmentation model. arXiv:2204.02681"},{"key":"5971_CR39","doi-asserted-by":"crossref","unstructured":"Strudel R, Garcia R, Laptev I, Schmid C (2021) Segmenter: Transformer for semantic segmentation. in 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE","DOI":"10.1109\/ICCV48922.2021.00717"},{"issue":"2021","key":"5971_CR40","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P (2021) Segformer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems 34(2021):12077\u201312090","journal-title":"Advances in neural information processing systems"},{"key":"5971_CR41","doi-asserted-by":"crossref","unstructured":"Zhang W, Huang Z, Luo G, Chen T, Wang X, Liu W, Yu G, Shen C (2022) Topformer: Token pyramid transformer for mobile semantic segmentation. in 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE","DOI":"10.1109\/CVPR52688.2022.01177"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05971-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05971-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05971-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T15:07:43Z","timestamp":1737385663000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05971-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["5971"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05971-4","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"5 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interest to this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The authors of the submitted manuscript declare that does not involve any ethical issues.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"163"}}