{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T02:59:32Z","timestamp":1783565972272,"version":"3.55.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100019943","name":"Center for Ocean Mega-Science, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["KEXUE2019GZ04"],"award-info":[{"award-number":["KEXUE2019GZ04"]}],"id":[{"id":"10.13039\/501100019943","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014103","name":"Key Technology Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["Soft Science Project 2023RKY02009"],"award-info":[{"award-number":["Soft Science Project 2023RKY02009"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00530-025-01846-x","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T09:16:43Z","timestamp":1747732603000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["DMFI-YOLO: dynamic multi-scale feature interaction for enhanced underwater object detection based on YOLO"],"prefix":"10.1007","volume":"31","author":[{"given":"Xueyu","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinzhi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingdi","family":"Bo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"key":"1846_CR1","unstructured":"Minar, M.R., Naher, J.: Recent advances in deep learning: an overview. arXiv preprint arXiv:1807.08169 (2018)"},{"key":"1846_CR2","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, Y., Jiang, X., Guo, Z., Gong, M., Cao, H., Liu, Y., Jiang, D., Sun, X.: Enhancing visual document understanding with contrastive learning in large visual-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15546\u201315555 (2024)","DOI":"10.1109\/CVPR52733.2024.01472"},{"key":"1846_CR3","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.: FoundationPose: unified 6D pose estimation and tracking of novel objects. arXiv:2312.08344 (2024)","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"1846_CR4","doi-asserted-by":"crossref","unstructured":"Ai, Y., Ling, Z.-H.: Neural speech phase prediction based on parallel estimation architecture and anti-wrapping losses. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096553"},{"key":"1846_CR5","doi-asserted-by":"crossref","unstructured":"Liu, C., Zhang, G., Zhao, R., Wang, L.: Sparse global matching for video frame interpolation with large motion. arXiv:2404.06913 (2024)","DOI":"10.1109\/CVPR52733.2024.01809"},{"key":"1846_CR6","doi-asserted-by":"crossref","unstructured":"Li, Z., Yang, L.T., Ren, B., Nie, X., Gao, Z., Tan, C., Li, S.Z.: MLIP: enhancing medical visual representation with divergence encoder and knowledge-guided contrastive learning. arXiv:2402.02045 (2024)","DOI":"10.1109\/CVPR52733.2024.01112"},{"key":"1846_CR7","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Yeh, I.-H., Liao, H.-Y.M.: Yolov9: learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616 (2024)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"1846_CR8","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: Yolov10: real-time end-to-end object detection. arXiv preprint arXiv:2405.14458 (2024)"},{"key":"1846_CR9","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: single shot multibox detector. In: Computer Vision\u2014ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"issue":"6","key":"1846_CR10","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1846_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L., Liu, Z., Tong, L., Jiang, Z., Wang, S., Dong, J., Zhou, H.: Underwater object detection using invert multi-class adaboost with deep learning. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207506"},{"key":"1846_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2022.101923","volume":"72","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Yongpan, W., Xianchong, X., Yong, L., Lyu, L., Wu, Q.: Yoloxt: a object detection algorithm for marine benthos. Ecol. Inform. 72, 101923 (2022)","journal-title":"Ecol. Inform."},{"key":"1846_CR13","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. arXiv:1611.05431 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"1846_CR14","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep Learning with Depthwise Separable Convolutions. arXiv:1610.02357 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"issue":"4","key":"1846_CR15","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.3390\/rs15041023","volume":"15","author":"Z Li","year":"2023","unstructured":"Li, Z., Li, J., Zhang, P., Zheng, L., Shen, Y., Li, Q., Li, X., Li, T.: A transfer-based framework for underwater target detection from hyperspectral imagery. Remote Sens. 15(4), 1023 (2023)","journal-title":"Remote Sens."},{"key":"1846_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2024.104052","volume":"98","author":"W Song","year":"2024","unstructured":"Song, W., Shen, Z., Zhang, M., Wang, Y., Liotta, A.: A hierarchical probabilistic underwater image enhancement model with reinforcement tuning. J. Vis. Commun. Image Represent. 98, 104052 (2024)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"1846_CR17","unstructured":"\u4e1b\u6653\u5cf0, \u6842\u6770,\u7ae0\u519b, et al.:\u57fa\u4e8e\u89c6\u89c9 transformer \u7684\u591a\u635f\u5931\u878d\u5408\u6c34\u4e0b\u56fe\u50cf\u589e\u5f3a\u7f51\u7edc.\u667a\u80fd\u79d1\u5b66\u4e0e\u6280\u672f\u5b66\u62a5 4(4), 522\u2013532 (2022)"},{"key":"1846_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., Zhu, Y., Chen, M., Wang, Y., Zhou, Z.: Research on underwater small target detection algorithm based on improved yolov3. In: 2022 16th IEEE International Conference on Signal Processing (ICSP), vol. 1, pp. 76\u201380. IEEE (2022)","DOI":"10.1109\/ICSP56322.2022.9965317"},{"issue":"3","key":"1846_CR19","doi-asserted-by":"publisher","first-page":"677","DOI":"10.3390\/jmse11030677","volume":"11","author":"K Liu","year":"2023","unstructured":"Liu, K., Sun, Q., Sun, D., Peng, L., Yang, M., Wang, N.: Underwater target detection based on improved yolov7. J. Mar. Sci. Eng. 11(3), 677 (2023)","journal-title":"J. Mar. Sci. Eng."},{"key":"1846_CR20","unstructured":"Zhu, M., Han, K., Yu, C., Wang, Y.: Dynamic Feature Pyramid Networks for Object Detection. arXiv:2012.00779 (2021)"},{"key":"1846_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102758","volume":"82","author":"J Feng","year":"2024","unstructured":"Feng, J., Jin, T.: Ceh-yolo: a composite enhanced yolo-based model for underwater object detection. Ecol. Inform. 82, 102758 (2024)","journal-title":"Ecol. Inform."},{"key":"1846_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102680","volume":"82","author":"H Zhou","year":"2024","unstructured":"Zhou, H., Kong, M., Yuan, H., Pan, Y., Wang, X., Chen, R., Lu, W., Wang, R., Yang, Q.: Real-time underwater object detection technology for complex underwater environments based on deep learning. Ecol. Inform. 82, 102680 (2024)","journal-title":"Ecol. Inform."},{"key":"1846_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2023.102022","volume":"75","author":"X Xu","year":"2023","unstructured":"Xu, X., Liu, Y., Lyu, L., Yan, P., Zhang, J.: Mad-yolo: a quantitative detection algorithm for dense small-scale marine benthos. Ecol. Inform. 75, 102022 (2023)","journal-title":"Ecol. Inform."},{"issue":"3","key":"1846_CR24","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1109\/JOE.2019.2911447","volume":"45","author":"Y Guo","year":"2019","unstructured":"Guo, Y., Li, H., Zhuang, P.: Underwater image enhancement using a multiscale dense generative adversarial network. IEEE J. Ocean. Eng. 45(3), 862\u2013870 (2019)","journal-title":"IEEE J. Ocean. Eng."},{"key":"1846_CR25","unstructured":"\u5218\u7693\u8f69,\u6797\u73ca\u73b2,\u6797\u5fd7\u8d24,\u90ed\u592a\u826f,\u6797\u575a\u666e, et al.:\u57fa\u4e8e gan \u7684\u8f7b\u91cf\u7ea7\u6c34\u4e0b\u56fe\u50cf\u589e\u5f3a\u7f51\u7edc.Chinese Journal of Liquid Crystals and Displays 38(3), 378\u2013386 (2023)"},{"issue":"1","key":"1846_CR26","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/rs13010054","volume":"13","author":"LJ Biffi","year":"2020","unstructured":"Biffi, L.J., Mitishita, E., Liesenberg, V., Santos, A.A.D., Goncalves, D.N., Estrabis, N.V., Silva, J.D.A., Osco, L.P., Ramos, A.P.M., Centeno, J.A.S., et al.: Atss deep learning-based approach to detect apple fruits. Remote Sens. 13(1), 54 (2020)","journal-title":"Remote Sens."},{"key":"1846_CR27","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: Tood: task-aligned one-stage object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3490\u20133499. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"1846_CR28","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"1846_CR29","doi-asserted-by":"publisher","unstructured":"Jocher, G.: ultralytics\/yolov5: V3.1-Bug Fixes and Performance Improvements. https:\/\/doi.org\/10.5281\/zenodo.4154370","DOI":"10.5281\/zenodo.4154370"},{"key":"1846_CR30","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al.: Yolov6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"1846_CR31","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1846_CR32","first-page":"51094","volume":"36","author":"C Wang","year":"2024","unstructured":"Wang, C., He, W., Nie, Y., Guo, J., Liu, C., Wang, Y., Han, K.: Gold-yolo: efficient object detector via gather-and-distribute mechanism. Adv. Neural Inf. Process. Syst. 36, 51094\u201351112 (2024)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1846_CR33","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: Ghostnet: more features from cheap operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1580\u20131589 (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"1846_CR34","doi-asserted-by":"crossref","unstructured":"Ouyang, D., He, S., Zhang, G., Luo, M., Guo, H., Zhan, J., Huang, Z.: Efficient multi-scale attention module with cross-spatial learning. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"1846_CR35","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1846_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: More deformable, better results. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316 (2019)","DOI":"10.1109\/CVPR.2019.00953"},{"key":"1846_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"1846_CR38","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1846_CR39","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: Keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"1846_CR40","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.neucom.2023.01.088","volume":"530","author":"P Song","year":"2023","unstructured":"Song, P., Li, P., Dai, L., Wang, T., Chen, Z.: Boosting r-cnn: reweighting r-cnn samples by rpn\u2019s error for underwater object detection. Neurocomputing 530, 150\u2013164 (2023)","journal-title":"Neurocomputing"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01846-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01846-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01846-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:05:41Z","timestamp":1757927141000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01846-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1846"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01846-x","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,20]]},"assertion":[{"value":"22 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"258"}}