{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T08:53:44Z","timestamp":1765961624806},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T00:00:00Z","timestamp":1672185600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T00:00:00Z","timestamp":1672185600000},"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":["SIViP"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s11760-022-02400-2","type":"journal-article","created":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T05:02:46Z","timestamp":1672203766000},"page":"1889-1896","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Lightweight Transformers make strong encoders for underwater object detection"],"prefix":"10.1007","volume":"17","author":[{"given":"Jinrong","family":"Cui","sequence":"first","affiliation":[]},{"given":"Hailong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Haowei","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Cheng","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Weifeng","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,28]]},"reference":[{"key":"2400_CR1","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., et\u00a0al.: Attention augmented convolutional networks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3286\u20133295 (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"2400_CR2","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection (2020). arXiv preprint arXiv:2004.10934"},{"key":"2400_CR3","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":"2400_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., et\u00a0al.: You only look one-level feature. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13,039\u201313,048 (2021)","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"2400_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"issue":"2","key":"2400_CR6","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., et al.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010). https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int. J. Comput. Vision"},{"issue":"6","key":"2400_CR7","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1007\/s11760-020-01841-x","volume":"15","author":"Z Fan","year":"2021","unstructured":"Fan, Z., Xia, W., Liu, X., et al.: Detection and segmentation of underwater objects from forward-looking sonar based on a modified Mask RCNN. SIViP 15(6), 1135\u20131143 (2021). https:\/\/doi.org\/10.1007\/s11760-020-01841-x","journal-title":"SIViP"},{"key":"2400_CR8","unstructured":"Fu, C.Y., Liu, W., Ranga, A., et\u00a0al.: DSSD : Deconvolutional Single Shot Detector (2017). arXiv:1701.06659 [cs] ArXiv: 1701.06659"},{"key":"2400_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., et\u00a0al.: Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. pp 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"2400_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: 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":"2400_CR11","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":"2400_CR12","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.neucom.2019.01.084","volume":"337","author":"H Huang","year":"2019","unstructured":"Huang, H., Zhou, H., Yang, X., et al.: Faster R-CNN for marine organisms detection and recognition using data augmentation. Neurocomputing 337, 372\u2013384 (2019). https:\/\/doi.org\/10.1016\/j.neucom.2019.01.084","journal-title":"Neurocomputing"},{"key":"2400_CR13","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":"2400_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., 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 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2400_CR15","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., et\u00a0al.: SSD: Single Shot MultiBox Detector. In: Leibe B, Matas J, Sebe N, et\u00a0al (eds) Computer Vision - ECCV 2016. Springer International Publishing, Cham, Lecture Notes in Computer Science, pp 21\u201337 (2016), https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2400_CR16","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 10,012\u201310,022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"5","key":"2400_CR17","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1007\/s11760-020-01818-w","volume":"15","author":"TS Pan","year":"2021","unstructured":"Pan, T.S., Huang, H.C., Lee, J.C., et al.: Multi-scale ResNet for real-time underwater object detection. SIViP 15(5), 941\u2013949 (2021). https:\/\/doi.org\/10.1007\/s11760-020-01818-w","journal-title":"SIViP"},{"key":"2400_CR18","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: An Incremental Improvement (2018). arXiv:1804.02767 [cs]"},{"key":"2400_CR19","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., et\u00a0al.: You Only Look Once: Unified, Real-Time Object Detection. pp 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"2400_CR20","doi-asserted-by":"publisher","unstructured":"Ren, S., He, K., Girshick, R., et\u00a0al.: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(6):1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031, conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence (2017)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"2400_CR21","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., et\u00a0al.: Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. pp 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2400_CR22","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.Y., Parmar, N., et\u00a0al.: Bottleneck Transformers for Visual Recognition. pp 16,519\u201316,529 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"2400_CR23","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., et\u00a0al.: FCOS: Fully Convolutional One-Stage Object Detection. pp 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2400_CR24","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"2400_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., et\u00a0al.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"2400_CR26","unstructured":"Zhang, X., Wan, F., Liu, C., et\u00a0al.: Freeanchor: Learning to match anchors for visual object detection. Advances in neural information processing systems 32 (2019)"},{"key":"2400_CR27","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points (2019). arXiv preprint arXiv:1904.07850"},{"key":"2400_CR28","unstructured":"Zhu, X., Su, W., Lu, L., et\u00a0al.: Deformable detr: Deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2020)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02400-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-022-02400-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02400-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,18]],"date-time":"2023-05-18T04:19:47Z","timestamp":1684383587000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-022-02400-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,28]]},"references-count":28,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["2400"],"URL":"https:\/\/doi.org\/10.1007\/s11760-022-02400-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,28]]},"assertion":[{"value":"27 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 December 2022","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 relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}