{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:48:49Z","timestamp":1775746129140,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s00138-024-01606-3","type":"journal-article","created":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T05:02:49Z","timestamp":1725253369000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Underwater image object detection based on multi-scale feature fusion"],"prefix":"10.1007","volume":"35","author":[{"given":"Chao","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longyu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"key":"1606_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed, A., Tangri ,P., Panda, A., et\u00a0al.: Vfnet: A convolutional architecture for accent classification. In: 2019 IEEE 16th India Council International Conference (INDICON), IEEE, pp 1\u20134 (2019)","DOI":"10.1109\/INDICON47234.2019.9030363"},{"key":"1606_CR2","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s00521-013-1544-2","volume":"27","author":"X Bai","year":"2016","unstructured":"Bai, X., Wang, W.: Principal pixel analysis and svm for automatic image segmentation. Neural Comput. Appl. 27, 45\u201358 (2016)","journal-title":"Neural Comput. Appl."},{"key":"1606_CR3","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s11749-016-0481-7","volume":"25","author":"G Biau","year":"2016","unstructured":"Biau, G., Scornet, E.: A random forest guided tour. TEST 25, 197\u2013227 (2016)","journal-title":"TEST"},{"key":"1606_CR4","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., et\u00a0al.: Yolact: Real-time instance segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9157\u20139166 (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"1606_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et\u00a0al.: End-to-end object detection with transformers. In: European conference on computer vision, Springer, pp 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1606_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Liu, Z., Tong, L., et\u00a0al.: Underwater object detection using invert multi-class adaboost with deep learning. In: 2020 International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1\u20138 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207506"},{"key":"1606_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., et\u00a0al.: Diffusiondet: Diffusion model for object detection. arXiv preprint arXiv:2211.09788 (2022)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"1606_CR8","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Li, Y., et\u00a0al.: Instance-sensitive fully convolutional networks. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI 14, Springer, pp 534\u2013549 (2016)","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"1606_CR9","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., et\u00a0al.: 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":"1606_CR10","unstructured":"Ge, Z., Liu, S., Wang, F., et\u00a0al.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1606_CR11","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, TY., Le, QV.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"1606_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., Fan, B., Zhang, Q., et\u00a0al.: Augfpn: Improving multi-scale feature learning for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12595\u201312604 (2020)","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"1606_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et\u00a0al.: Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1606_CR14","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1606_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., Huang, L., Gong, Y., et\u00a0al.: Mask scoring r-cnn. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6409\u20136418 (2019)","DOI":"10.1109\/CVPR.2019.00657"},{"key":"1606_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2020.101088","volume":"57","author":"A Jalal","year":"2020","unstructured":"Jalal, A., Salman, A., Mian, A., et al.: Fish detection and species classification in underwater environments using deep learning with temporal information. Eco. Inform. 57, 101088 (2020)","journal-title":"Eco. Inform."},{"key":"1606_CR17","doi-asserted-by":"crossref","unstructured":"Kim, B., Yu, SC.: Imaging sonar based real-time underwater object detection utilizing adaboost method. In: 2017 IEEE Underwater Technology (UT), IEEE, pp 1\u20135 (2017)","DOI":"10.1109\/UT.2017.7890300"},{"key":"1606_CR18","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s10462-011-9272-4","volume":"39","author":"SB Kotsiantis","year":"2013","unstructured":"Kotsiantis, S.B.: Decision trees: a recent overview. Artif. Intell. Rev. 39, 261\u2013283 (2013)","journal-title":"Artif. Intell. Rev."},{"key":"1606_CR19","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"1606_CR20","doi-asserted-by":"crossref","unstructured":"Liang, X., Song, P.: Excavating roi attention for underwater object detection. In: 2022 IEEE International Conference on Image Processing (ICIP), IEEE, pp 2651\u20132655 (2022)","DOI":"10.1109\/ICIP46576.2022.9897515"},{"key":"1606_CR21","doi-asserted-by":"crossref","unstructured":"Lin, TY., Doll\u00e1r, P., Girshick, R., et\u00a0al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125 (2017a)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1606_CR22","doi-asserted-by":"crossref","unstructured":"Lin, TY., Goyal, P., Girshick, R., et\u00a0al.: Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988 (2017b)","DOI":"10.1109\/ICCV.2017.324"},{"issue":"2","key":"1606_CR23","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1007\/s10044-023-01152-0","volume":"26","author":"M Liu","year":"2023","unstructured":"Liu, M., Lin, K., Huo, W., et al.: Feature enhancement modules applied to a feature pyramid network for object detection. Pattern Anal. Appl. 26(2), 617\u2013629 (2023)","journal-title":"Pattern Anal. Appl."},{"issue":"3","key":"1606_CR24","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1007\/s10044-023-01173-9","volume":"26","author":"Z Liu","year":"2023","unstructured":"Liu, Z., Cheng, J.: Cb-fpn: object detection feature pyramid network based on context information and bidirectional efficient fusion. Pattern Anal. Appl. 26(3), 1441\u20131452 (2023)","journal-title":"Pattern Anal. Appl."},{"key":"1606_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et\u00a0al.: 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"},{"issue":"21","key":"1606_CR26","doi-asserted-by":"publisher","first-page":"30685","DOI":"10.1007\/s11042-022-11940-1","volume":"81","author":"Y Luo","year":"2022","unstructured":"Luo, Y., Cao, X., Zhang, J., et al.: Ce-fpn: Enhancing channel information for object detection. Multimed. Tools Appl. 81(21), 30685\u201330704 (2022)","journal-title":"Multimed. Tools Appl."},{"issue":"3","key":"1606_CR27","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/0098-3004(93)90090-R","volume":"19","author":"A Ma\u0107kiewicz","year":"1993","unstructured":"Ma\u0107kiewicz, A., Ratajczak, W.: Principal components analysis (pca). Comput. Geosci. 19(3), 303\u2013342 (1993)","journal-title":"Comput. Geosci."},{"key":"1606_CR28","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s00530-011-0244-y","volume":"18","author":"Y Nakashima","year":"2012","unstructured":"Nakashima, Y., Babaguchi, N., Fan, J.: Intended human object detection for automatically protecting privacy in mobile video surveillance. Multimed. Syst. 18, 157\u2013173 (2012)","journal-title":"Multimed. Syst."},{"key":"1606_CR29","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., et\u00a0al.: Libra r-cnn: Towards balanced learning for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 821\u2013830 (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1606_CR30","first-page":"2784","volume-title":"ICASSP 2022\u20132022 IEEE international conference on Acoustics","author":"S Qi","year":"2022","unstructured":"Qi, S., Du, J., Wu, M., et al.: Underwater small target detection based on deformable convolutional pyramid. In: ICASSP 2022\u20132022 IEEE international conference on Acoustics, pp. 2784\u20132788. IEEE, Speech and Signal Processing (ICASSP) (2022)"},{"key":"1606_CR31","unstructured":"Ren, S., He, K., Girshick, R., et\u00a0al.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"1606_CR32","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., et al.: Boosting r-cnn: Reweighting r-cnn samples by rpn\u2019s error for underwater object detection. Neurocomputing 530, 150\u2013164 (2023)","journal-title":"Neurocomputing"},{"key":"1606_CR33","doi-asserted-by":"crossref","unstructured":"Song, W., Fu, C., Zheng, Y., et\u00a0al.: Protection of image roi using chaos-based encryption and dcnn-based object detection. Neural Comput. Appl. 1\u201314 (2022)","DOI":"10.1007\/s00521-021-06725-w"},{"key":"1606_CR34","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., et\u00a0al.: Sparse r-cnn: End-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"1606_CR35","doi-asserted-by":"crossref","unstructured":"Sung, M., Yu, SC., Girdhar, Y.: Vision based real-time fish detection using convolutional neural network. In: OCEANS 2017-Aberdeen, IEEE, pp 1\u20136 (2017)","DOI":"10.1109\/OCEANSE.2017.8084889"},{"key":"1606_CR36","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., et\u00a0al.: Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1606_CR37","doi-asserted-by":"crossref","unstructured":"Villon, S., Chaumont, M., Subsol, G., et\u00a0al.: Coral reef fish detection and recognition in underwater videos by supervised machine learning: Comparison between deep learning and hog+ svm methods. In: International Conference on Advanced Concepts for Intelligent Vision Systems, Springer, pp 160\u2013171 (2016)","DOI":"10.1007\/978-3-319-48680-2_15"},{"issue":"1","key":"1606_CR38","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/s00530-022-00983-x","volume":"29","author":"H Wang","year":"2023","unstructured":"Wang, H., Song, Y., Huo, L., et al.: Multiscale object detection based on channel and data enhancement at construction sites. Multimed. Syst. 29(1), 49\u201358 (2023)","journal-title":"Multimed. Syst."},{"key":"1606_CR39","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, JH., Zou, Y., et\u00a0al.: Panet: Few-shot image semantic segmentation with prototype alignment. In: proceedings of the IEEE\/CVF international conference on computer vision, pp 9197\u20139206 (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"1606_CR40","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1007\/s10044-021-00989-7","volume":"24","author":"C Xianbao","year":"2021","unstructured":"Xianbao, C., Guihua, Q., Yu, J., et al.: An improved small object detection method based on yolo v3. Pattern Anal. Appl. 24, 1347\u20131355 (2021)","journal-title":"Pattern Anal. Appl."},{"key":"1606_CR41","doi-asserted-by":"publisher","first-page":"3637","DOI":"10.1007\/s00521-020-05217-7","volume":"33","author":"F Xu","year":"2021","unstructured":"Xu, F., Wang, H., Peng, J., et al.: Scale-aware feature pyramid architecture for marine object detection. Neural Comput. Appl. 33, 3637\u20133653 (2021)","journal-title":"Neural Comput. Appl."},{"issue":"17","key":"1606_CR42","doi-asserted-by":"publisher","first-page":"14881","DOI":"10.1007\/s00521-022-07264-8","volume":"34","author":"F Xu","year":"2022","unstructured":"Xu, F., Wang, H., Sun, X., et al.: Refined marine object detector with attention-based spatial pyramid pooling networks and bidirectional feature fusion strategy. Neural Comput. Appl. 34(17), 14881\u201314894 (2022)","journal-title":"Neural Comput. Appl."},{"issue":"4","key":"1606_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-023-01406-1","volume":"34","author":"C Yang","year":"2023","unstructured":"Yang, C., Li, Y., Jiang, L., et al.: Foreground enhancement network for object detection in sonar images. Mach. Vis. Appl. 34(4), 1\u201314 (2023)","journal-title":"Mach. Vis. Appl."},{"key":"1606_CR44","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s00530-014-0361-5","volume":"21","author":"L Ying","year":"2015","unstructured":"Ying, L., Zhang, T., Xu, C.: Multi-object tracking via mht with multiple information fusion in surveillance video. Multimed. Syst. 21, 313\u2013326 (2015)","journal-title":"Multimed. Syst."},{"issue":"2","key":"1606_CR45","doi-asserted-by":"publisher","first-page":"2280","DOI":"10.1007\/s10489-022-03396-5","volume":"53","author":"SX Zhang","year":"2023","unstructured":"Zhang, S.X., Zhu, X., Hou, J.B., et al.: Graph fusion network for multi-oriented object detection. Appl. Intell. 53(2), 2280\u20132294 (2023)","journal-title":"Appl. Intell."},{"key":"1606_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., et\u00a0al.: Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01606-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-024-01606-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01606-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T22:05:16Z","timestamp":1731017116000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-024-01606-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":46,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["1606"],"URL":"https:\/\/doi.org\/10.1007\/s00138-024-01606-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4114831\/v1","asserted-by":"object"}]},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,2]]},"assertion":[{"value":"16 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare relevant to this article\u2019s content","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"124"}}