{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:08:13Z","timestamp":1783570093941,"version":"3.55.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Basic Research Project of Yantai Science and Technology Innovation Development Plan","award":["2023JCYJ044"],"award-info":[{"award-number":["2023JCYJ044"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62007017,  U24A20328"],"award-info":[{"award-number":["62007017,  U24A20328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Shandong Province of China","award":["ZR2022MF231"],"award-info":[{"award-number":["ZR2022MF231"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s00371-025-04097-z","type":"journal-article","created":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T08:01:53Z","timestamp":1752307313000},"page":"11207-11219","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Hybrid transformer-CNN architecture for enhanced underwater image semantic segmentation"],"prefix":"10.1007","volume":"41","author":[{"given":"Jiaxing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,12]]},"reference":[{"issue":"3","key":"4097_CR1","doi-asserted-by":"publisher","first-page":"310","DOI":"10.3390\/jmse10030310","volume":"10","author":"F Lei","year":"2022","unstructured":"Lei, F., Tang, F., Li, S.: Underwater target detection algorithm based on improved yolov5. J. Marine Sci. Eng. 10(3), 310 (2022)","journal-title":"J. Marine Sci. Eng."},{"issue":"1","key":"4097_CR2","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1109\/TIP.2017.2759252","volume":"27","author":"CO Ancuti","year":"2017","unstructured":"Ancuti, C.O., Ancuti, C., De Vleeschouwer, C., Bekaert, P.: Color balance and fusion for underwater image enhancement. IEEE Trans. Image Process. 27(1), 379\u2013393 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"4097_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104171","volume":"101","author":"P Zhuang","year":"2021","unstructured":"Zhuang, P., Li, C., Wu, J.: Bayesian retinex underwater image enhancement. Eng. Appl. Artif. Intell. 101, 104171 (2021)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"9","key":"4097_CR4","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1049\/ipr2.12172","volume":"15","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Sun, L., Wu, L., Gu, K.: Dugan: An effective framework for underwater image enhancement. IET Image Proc. 15(9), 2010\u20132019 (2021)","journal-title":"IET Image Proc."},{"key":"4097_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108926","volume":"132","author":"L Chen","year":"2022","unstructured":"Chen, L., Zhou, F., Wang, S., Dong, J., Li, N., Ma, H., Wang, X., Zhou, H.: Swipenet: Object detection in noisy underwater scenes. Pattern Recogn. 132, 108926 (2022)","journal-title":"Pattern Recogn."},{"key":"4097_CR6","unstructured":"Li, X., Shang, M., Qin, H., Chen, L.: Fast accurate fish detection and recognition of underwater images with fast r-cnn. In: OCEANS 2015-MTS\/IEEE Washington, pp. 1\u20135 (2015)"},{"issue":"3","key":"4097_CR7","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1007\/s00371-024-03448-6","volume":"41","author":"Y Li","year":"2024","unstructured":"Li, Y., Li, Z., Liu, H., Wang, Q.: Zmnet: feature fusion and semantic boundary supervision for real-time semantic segmentation. Vis. Comput. 41(3), 1543\u20131554 (2024)","journal-title":"Vis. Comput."},{"key":"4097_CR8","doi-asserted-by":"crossref","unstructured":"Ali, S.G., Wang, X., Li, P., Li, H., Yang, P., Jung, Y., Qin, J., Kim, J., Sheng, B.: Egdnet: an efficient glomerular detection network for multiple anomalous pathological feature in glomerulonephritis. The Visual Computer, 1\u201318 (2024)","DOI":"10.1007\/s00371-024-03570-5"},{"key":"4097_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107673","volume":"130","author":"KB Ryu","year":"2024","unstructured":"Ryu, K.B., Kang, S.J., Jeong, S.I., Jeong, M.S., Park, K.R.: Cn4srss: Combined network for super-resolution reconstruction and semantic segmentation in frontal-viewing camera images of vehicle. Eng. Appl. Artif. Intell. 130, 107673 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"4097_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.sasc.2024.200172","volume":"6","author":"S Li","year":"2024","unstructured":"Li, S., Huang, C.: Using convolutional neural networks for image semantic segmentation and object detection. Syst. Soft Comput. 6, 200172 (2024)","journal-title":"Syst. Soft Comput."},{"issue":"6","key":"4097_CR11","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"4097_CR12","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.patrec.2021.04.024","volume":"148","author":"Y Jin","year":"2021","unstructured":"Jin, Y., Han, D., Ko, H.: Trseg: Transformer for semantic segmentation. Pattern Recogn. Lett. 148, 29\u201335 (2021)","journal-title":"Pattern Recogn. Lett."},{"key":"4097_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106669","volume":"126","author":"H Thisanke","year":"2023","unstructured":"Thisanke, H., Deshan, C., Chamith, K., Seneviratne, S., Vidanaarachchi, R., Herath, D.: Semantic segmentation using vision transformers: A survey. Eng. Appl. Artif. Intell. 126, 106669 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"4097_CR14","doi-asserted-by":"crossref","unstructured":"Akkaynak, D., Treibitz, T., Shlesinger, T., Loya, Y., Tamir, R., Iluz, D.: What is the space of attenuation coefficients in underwater computer vision? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4931\u20134940 (2017)","DOI":"10.1109\/CVPR.2017.68"},{"key":"4097_CR15","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"4097_CR16","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-assisted intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"4097_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"issue":"4","key":"4097_CR18","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4097_CR19","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arxiv. arXiv preprint arXiv:1706.05587 5 (2017)"},{"key":"4097_CR20","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"4097_CR21","doi-asserted-by":"crossref","unstructured":"Huynh, C., Tran, A.T., Luu, K., Hoai, M.: Progressive semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16755\u201316764 (2021)","DOI":"10.1109\/CVPR46437.2021.01648"},{"issue":"12","key":"4097_CR22","doi-asserted-by":"publisher","first-page":"3446","DOI":"10.1109\/TMI.2021.3087857","volume":"40","author":"R Liu","year":"2021","unstructured":"Liu, R., Liu, M., Sheng, B., Li, H., Li, P., Song, H., Zhang, P., Jiang, L., Shen, D.: Nhbs-net: A feature fusion attention network for ultrasound neonatal hip bone segmentation. IEEE Trans. Med. Imaging 40(12), 3446\u20133458 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"4097_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121999","volume":"238","author":"X Fan","year":"2024","unstructured":"Fan, X., Zhou, W., Qian, X., Yan, W.: Progressive adjacent-layer coordination symmetric cascade network for semantic segmentation of multimodal remote sensing images. Expert Syst. Appl. 238, 121999 (2024)","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"4097_CR24","doi-asserted-by":"publisher","first-page":"93","DOI":"10.3390\/jmse6030093","volume":"6","author":"M O\u2019Byrne","year":"2018","unstructured":"O\u2019Byrne, M., Pakrashi, V., Schoefs, F., Ghosh, B.: Semantic segmentation of underwater imagery using deep networks trained on synthetic imagery. J. Marine Sci. Eng. 6(3), 93 (2018)","journal-title":"J. Marine Sci. Eng."},{"issue":"3","key":"4097_CR25","doi-asserted-by":"publisher","first-page":"188","DOI":"10.3390\/jmse8030188","volume":"8","author":"F Liu","year":"2020","unstructured":"Liu, F., Fang, M.: Semantic segmentation of underwater images based on improved deeplab. J. Marine Sci. Eng. 8(3), 188 (2020)","journal-title":"J. Marine Sci. Eng."},{"key":"4097_CR26","doi-asserted-by":"crossref","unstructured":"Wang, J., He, X., Shao, F., Lu, G., Hu, R., Jiang, Q.: Semantic segmentation method of underwater images based on encoder-decoder architecture. PLoS ONE 17(8), 0272666 (2022)","DOI":"10.1371\/journal.pone.0272666"},{"key":"4097_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"4097_CR28","first-page":"4971","volume":"35","author":"B Zhang","year":"2022","unstructured":"Zhang, B., Tian, Z., Tang, Q., Chu, X., Wei, X., Shen, C., et al.: Segvit: Semantic segmentation with plain vision transformers. Adv. Neural. Inf. Process. Syst. 35, 4971\u20134982 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4097_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106205","volume":"93","author":"P Geng","year":"2024","unstructured":"Geng, P., Tan, Z., Wang, Y., Jia, W., Zhang, Y., Yan, H.: Stcnet: Alternating cnn and improved transformer network for covid-19 ct image segmentation. Biomed. Signal Process. Control 93, 106205 (2024)","journal-title":"Biomed. Signal Process. Control"},{"key":"4097_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110491","volume":"152","author":"X Guo","year":"2024","unstructured":"Guo, X., Lin, X., Yang, X., Yu, L., Cheng, K.-T., Yan, Z.: Uctnet: Uncertainty-guided cnn-transformer hybrid networks for medical image segmentation. Pattern Recogn. 152, 110491 (2024)","journal-title":"Pattern Recogn."},{"key":"4097_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, H., Hu, Q.: Transfuse: Fusing transformers and cnns for medical image segmentation. In: Medical Image Computing and Computer Assisted intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24, pp. 14\u201324 (2021)","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"4097_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4097_CR33","doi-asserted-by":"crossref","unstructured":"Islam, M.J., Edge, C., Xiao, Y., Luo, P., Mehtaz, M., Morse, C., Enan, S.S., Sattar, J.: Semantic segmentation of underwater imagery: Dataset and benchmark. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1769\u20131776 (2020)","DOI":"10.1109\/IROS45743.2020.9340821"},{"key":"4097_CR34","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., Zhou, Y.: Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"4097_CR35","doi-asserted-by":"crossref","unstructured":"Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Garcia-Rodriguez, J.: A review on deep learning techniques applied to semantic segmentation. arXiv preprint arXiv:1704.06857 (2017)","DOI":"10.1016\/j.asoc.2018.05.018"},{"key":"4097_CR36","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van\u00a0Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"issue":"2","key":"4097_CR37","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/TMI.2019.2930068","volume":"39","author":"D Karimi","year":"2020","unstructured":"Karimi, D., Salcudean, S.E.: Reducing the hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Trans. Med. Imaging 39(2), 499\u2013513 (2020)","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04097-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04097-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04097-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T14:00:01Z","timestamp":1758722401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04097-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,12]]},"references-count":37,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["4097"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04097-z","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,12]]},"assertion":[{"value":"25 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2025","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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}