{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T03:26:38Z","timestamp":1773890798104,"version":"3.50.1"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"China National Offshore Oil Corp (CNOOC) Research Center,the National Natural Science Foundation of China Project","award":["51409059"],"award-info":[{"award-number":["51409059"]}]},{"name":"Equipment Pre-research Key Laboratory","award":["6142215190207"],"award-info":[{"award-number":["6142215190207"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s10846-023-02020-z","type":"journal-article","created":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T08:01:30Z","timestamp":1702713690000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Visual Detection Algorithm for Enhanced Environmental Perception of Unmanned Surface Vehicles in Complex Marine Environments"],"prefix":"10.1007","volume":"110","author":[{"given":"Kaiyuan","family":"Dong","sequence":"first","affiliation":[]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Hongwang","family":"Du","sequence":"additional","affiliation":[]},{"given":"Xianfeng","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,16]]},"reference":[{"key":"2020_CR1","doi-asserted-by":"crossref","unstructured":"Pan, Z., Cai, J., Zhuang, B.: Stitchable neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 16102\u201316112 (2023)","DOI":"10.1109\/CVPR52729.2023.01545"},{"key":"2020_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, L., Qiao, Y., Gao, P., Li, H.: Learning 3d representations from 2d pre-trained models via image-to-point masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 21769\u201321780 (2023)","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"2020_CR3","doi-asserted-by":"crossref","unstructured":"Yu, S., Sohn, K., Kim, S., Shin, J.: Video probabilistic diffusion models in projected latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18456\u201318466 (2023)","DOI":"10.1109\/CVPR52729.2023.01770"},{"issue":"2","key":"2020_CR4","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s10846-023-01953-9","volume":"109","author":"Y Yuan","year":"2023","unstructured":"Yuan, Y., Yang, J., Yu, Z.L., Cheng, Y., Jiao, P., Hua, L.: Hierarchical goal-guided learning for the evasive maneuver of fixed-wing uavs based on deep reinforcement learning. J. Intell. Robot. Syst. 109(2), 43 (2023)","journal-title":"J. Intell. Robot. Syst."},{"key":"2020_CR5","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. (2014) arXiv:1409.1556"},{"key":"2020_CR6","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2020_CR7","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":"2020_CR8","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"2020_CR9","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":"2020_CR10","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. (2017) arXiv:1706.05587"},{"key":"2020_CR11","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"},{"key":"2020_CR12","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention. Springer pp. 234\u2013241(2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"12","key":"2020_CR13","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2020_CR14","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"2020_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, J., Liu, R., Shi, H., Yang, K., Rei\u00df, S., Peng, K., Fu, H., Wang, K., Stiefelhagen, R.: Delivering arbitrary-modal semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1136\u20131147 (2023)","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"2020_CR16","doi-asserted-by":"crossref","unstructured":"Jia, D., Yuan, Y., He, H., Wu, X., Yu, H., Lin, W., Sun, L., Zhang, C., Hu, H.: Detrs with hybrid matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 19702\u201319712 (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"2020_CR17","doi-asserted-by":"crossref","unstructured":"Chen, F., Zhang, H., Hu, K., Huang, Y.-K., Zhu, C., Savvides, M.: Enhanced training of query-based object detection via selective query recollection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 23756\u201323765 (2023)","DOI":"10.1109\/CVPR52729.2023.02275"},{"key":"2020_CR18","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"9","key":"2020_CR19","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2020_CR20","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"2020_CR21","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process Syst. 28 (2015)"},{"key":"2020_CR22","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: Delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2020_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2020_CR24","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: European Conference on Computer Vision. Springer pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2020_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: 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":"2020_CR26","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"2020_CR27","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"2020_CR28","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. (2018) arXiv:1804.02767"},{"key":"2020_CR29","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. (2020) arXiv:2004.10934"},{"key":"2020_CR30","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. (2021) arXiv:2107.08430"},{"key":"2020_CR31","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":"2020_CR32","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":"2020_CR33","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":"2020_CR34","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: 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"},{"issue":"7","key":"2020_CR35","doi-asserted-by":"publisher","first-page":"753","DOI":"10.3390\/jmse9070753","volume":"9","author":"T Liu","year":"2021","unstructured":"Liu, T., Pang, B., Zhang, L., Yang, W., Sun, X.: Sea surface object detection algorithm based on yolo v4 fused with reverse depthwise separable convolution (rdsc) for usv. J. Mar. Sci. Eng. 9(7), 753 (2021)","journal-title":"J. Mar. Sci. Eng."},{"issue":"24","key":"2020_CR36","doi-asserted-by":"publisher","first-page":"7263","DOI":"10.3390\/s20247263","volume":"20","author":"T Liu","year":"2020","unstructured":"Liu, T., Pang, B., Ai, S., Sun, X.: Study on visual detection algorithm of sea surface targets based on improved yolov3. Sensors. 20(24), 7263 (2020)","journal-title":"Sensors."},{"issue":"3","key":"2020_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-021-01499-8","volume":"103","author":"X Sun","year":"2021","unstructured":"Sun, X., Liu, T., Yu, X., Pang, B.: Unmanned surface vessel visual object detection under all-weather conditions with optimized feature fusion network in yolov4. J Intell. Robot. Syst. 103(3), 1\u201316 (2021)","journal-title":"J Intell. Robot. Syst."},{"key":"2020_CR38","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., Yeh, I.-H.: Cspnet: A new backbone that can enhance learning capability of cnn. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"2020_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, D., Zhang, H., Tang, J., Wang, M., Hua, X., Sun, Q.: Feature pyramid transformer. In: European Conference on Computer Vision. Springer pp. 323\u2013339 (2020)","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"2020_CR40","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. (2020) arXiv:2010.11929"},{"key":"2020_CR41","doi-asserted-by":"crossref","unstructured":"Takashima, S., Hayamizu, R., Inoue, N., Kataoka, H., Yokota, R.: Visual atoms: Pre-training vision transformers with sinusoidal waves. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18579\u201318588 (2023)","DOI":"10.1109\/CVPR52729.2023.01782"},{"key":"2020_CR42","doi-asserted-by":"crossref","unstructured":"Nakhli, R., Moghadam, P.A., Mi, H., Farahani, H., Baras, A., Gilks, B., Bashashati, A.: Sparse multi-modal graph transformer with shared-context processing for representation learning of giga-pixel images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11547\u201311557 (2023)","DOI":"10.1109\/CVPR52729.2023.01111"},{"issue":"2","key":"2020_CR43","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1080\/2150704X.2020.1837988","volume":"12","author":"J Wang","year":"2021","unstructured":"Wang, J., Lin, Y., Guo, J., Zhuang, L.: Sss-yolo: Towards more accurate detection for small ships in sar image. Remote Sens. Lett. 12(2), 93\u2013102 (2021)","journal-title":"Remote Sens. Lett."},{"issue":"2","key":"2020_CR44","doi-asserted-by":"publisher","first-page":"308","DOI":"10.3390\/sym13020308","volume":"13","author":"Y Jie","year":"2021","unstructured":"Jie, Y., Leonidas, L., Mumtaz, F., Ali, M.: Ship detection and tracking in inland waterways using improved yolov3 and deep sort. Symmetry. 13(2), 308 (2021)","journal-title":"Symmetry."},{"key":"2020_CR45","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":"2020_CR46","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2020_CR47","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"2020_CR48","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, S.-h., He, H., Zhuo, W., Wen, S., Lee, C.-H., Chan, S.-H.G.: Run, don\u2019t walk: Chasing higher flops for faster neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12021\u201312031 (2023)","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"2020_CR49","doi-asserted-by":"crossref","unstructured":"Tian, Y., Xie, L., Wang, Z., Wei, L., Zhang, X., Jiao, J., Wang, Y., Tian, Q., Ye, Q.: Integrally pre-trained transformer pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18610\u201318620 (2023)","DOI":"10.1109\/CVPR52729.2023.01785"},{"key":"2020_CR50","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":"2020_CR51","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et al.: Swin transformer v2: Scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"2020_CR52","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: Repvgg: Making vgg-style convnets great again. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13733\u201313742 (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"2020_CR53","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":"2020_CR54","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2020_CR55","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2020_CR56","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. Ieee pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"2020_CR57","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: A retrospective. Int. J. Comput. Vision 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"2020_CR58","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":"2020_CR59","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: A metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2020_CR60","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: Faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34. pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"2020_CR61","unstructured":"Gevorgyan, Z.: Siou loss: More powerful learning for bounding box regression. (2022) arXiv:2205.12740"},{"key":"2020_CR62","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"issue":"8","key":"2020_CR63","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TITS.2016.2634580","volume":"18","author":"DK Prasad","year":"2017","unstructured":"Prasad, D.K., Rajan, D., Rachmawati, L., Rajabally, E., Quek, C.: Video processing from electro-optical sensors for object detection and tracking in a maritime environment: A survey. IEEE Trans. Intell. Transp. Syst. 18(8), 1993\u20132016 (2017)","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-023-02020-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-023-02020-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-023-02020-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T02:14:46Z","timestamp":1711937686000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-023-02020-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":63,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["2020"],"URL":"https:\/\/doi.org\/10.1007\/s10846-023-02020-z","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,16]]},"assertion":[{"value":"6 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2023","order":3,"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":"Conflicts of interest"}},{"value":"All procedures performed in this study were in accordance with with the ethical standards of the institution and the National Research Council.Approval was obtained from the ethics committee of Harbin Engineering University.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"The authors affirm that research participants provided informed consent for publication of their data and photographs.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"1"}}