{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:46:02Z","timestamp":1757540762207,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T00:00:00Z","timestamp":1702857600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T00:00:00Z","timestamp":1702857600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61501251, 62071242"],"award-info":[{"award-number":["61501251, 62071242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17817-1","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T08:02:16Z","timestamp":1702886536000},"page":"56261-56273","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Improved YOLOv4 based on dilated coordinate attention for object detection"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5763-2768","authenticated-orcid":false,"given":"Zhenzhen","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongpeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,18]]},"reference":[{"issue":"6","key":"17817_CR1","doi-asserted-by":"publisher","first-page":"9243","DOI":"10.1007\/s11042-022-13644-y","volume":"82","author":"T Diwan","year":"2023","unstructured":"Diwan T, Anirudh G, Tembhurne J (2023) Object detection using YOLO: challenges, architectural successors, datasets and applications. Multimedia Tools Appl 82(6):9243\u20139275","journal-title":"Multimedia Tools Appl"},{"issue":"3","key":"17817_CR2","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou Z, Chen K, Shi Z et al (2023) Object detection in 20 years: a survey. Proc IEEE 111(3):257\u2013276","journal-title":"Proc IEEE"},{"key":"17817_CR3","doi-asserted-by":"crossref","unstructured":"Burger W, Burge M (2022) Scale-invariant feature transform (SIFT). Digital Image Process 709\u2013763","DOI":"10.1007\/978-3-031-05744-1_25"},{"key":"17817_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.petrol.2021.109971","volume":"209","author":"E Hosseini-Fard","year":"2022","unstructured":"Hosseini-Fard E, Roshandel-Kahoo A, Soleimani-Monfared M et al (2022) Automatic seismic image segmentation by introducing a novel strategy in histogram of oriented gradients. J Pet Sci Eng 209:1\u201316","journal-title":"J Pet Sci Eng"},{"key":"17817_CR5","first-page":"1","volume":"70","author":"G Li","year":"2021","unstructured":"Li G, Wu J, Deng C et al (2021) Convolutional neural network-based Bayesian Gaussian mixture for intelligent fault diagnosis of rotating machinery. IEEE Trans Instrum Meas 70:1\u201310","journal-title":"IEEE Trans Instrum Meas"},{"issue":"6","key":"17817_CR6","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1109\/TIP.2018.2809606","volume":"27","author":"M Zhang","year":"2018","unstructured":"Zhang M, Li W, Du Q (2018) Diverse region-based CNN for hyperspectral image classification. IEEE Trans Image Process 27(6):2623\u20132634","journal-title":"IEEE Trans Image Process"},{"issue":"9","key":"17817_CR7","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 (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17817_CR8","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.neucom.2021.11.100","volume":"490","author":"W Zhou","year":"2022","unstructured":"Zhou W, Liu C, Lei J et al (2022) HFNet: hierarchical feedback network with multilevel atrous spatial pyramid pooling for RGB-D saliency detection. Neurocomputing 490:347\u2013357","journal-title":"Neurocomputing"},{"issue":"4","key":"17817_CR9","first-page":"985","volume":"20","author":"J Li","year":"2017","unstructured":"Li J, Liang X, Shen S et al (2017) Scale-aware fast R-CNN for pedestrian detection. IEEE Trans Multimedia 20(4):985\u2013996","journal-title":"IEEE Trans Multimedia"},{"issue":"6","key":"17817_CR10","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"17817_CR11","doi-asserted-by":"publisher","first-page":"7423","DOI":"10.1109\/TII.2021.3056554","volume":"17","author":"Y Zhang","year":"2021","unstructured":"Zhang Y, Liu M, Yang Y et al (2021) A unified light framework for real-time fault detection of freight train images. IEEE Trans Ind Inform 17(11):7423\u20137432","journal-title":"IEEE Trans Ind Inform"},{"key":"17817_CR12","doi-asserted-by":"crossref","unstructured":"Lin T, Goyal P, Girshick R et al (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer Vision (ICCV), pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"17817_CR13","unstructured":"Tan M, Le Q (2019) EfficientNet: rethinking model scaling for convolutional neural networks. In: Proceedings of international conference on machine learning(ICML), pp 1\u201311"},{"key":"17817_CR14","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le Q (2020) Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"17817_CR15","first-page":"21","volume-title":"2016 European conference on computer vision (ECCV), 9905","author":"W Liu","year":"2016","unstructured":"Liu W, Anguelov D, Erhan D et al (2016) SSD: single shot multibox detector. 2016 European conference on computer vision (ECCV), 9905. The Netherlands, Amsterdam, pp 21\u201337"},{"key":"17817_CR16","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R et al (2016) You only look once: unified,real-time object detection. IEEE conference on computer vision and pattern recognition (CVPR), pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"17817_CR17","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. IEEE conference on computer vision and pattern recognition (CVPR), pp 6517\u20136525","DOI":"10.1109\/CVPR.2017.690"},{"key":"17817_CR18","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. arXiv:1804.02767"},{"key":"17817_CR19","unstructured":"Bochkovskiy A, Wang C, Liao H (2020) YOLOv4: optimal speed and accuracy of object detection. arXiv:2004.10934"},{"key":"17817_CR20","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"6","key":"17817_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/electronics9060889","volume":"9","author":"C Dewi","year":"2020","unstructured":"Dewi C (2020) Evaluation of robust spatial pyramid pooling based on convolutional neural network for traffic sign recognition system. Electronics 9(6):1\u201324","journal-title":"Electronics"},{"key":"17817_CR22","unstructured":"Yu F (2016) Multi\u2013scale context aggregation by dilated convolutions. arXiv:1511.07122v3"},{"key":"17817_CR23","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhou D, Feng J (2021) Coordinate attention for efficient mobile network design. IEEE conference on computer vision and pattern recognition (CVPR), pp 1\u201310","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"17817_CR24","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. ICLR, pp 1\u201314"},{"key":"17817_CR25","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"17817_CR26","unstructured":"Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. International conference on machine learning, pp 6105\u20136114"},{"key":"17817_CR27","doi-asserted-by":"crossref","unstructured":"Wang C, Liao H, Wu Y et al (2020) CSPNet: a new backbone that can enhance learning capability of CNN. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 390\u2013391","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"17817_CR28","unstructured":"Dai J, Li Y, He K et al (2016) R\u2013fcn: object detection via region\u2013based fully convolutional networks. Advances in neural information processing systems, pp 1\u20139"},{"issue":"2","key":"17817_CR29","first-page":"91","volume":"65","author":"A Kumar","year":"2013","unstructured":"Kumar A, Banno A, Ono S et al (2013) Global coordinate adjustment of the 3D survey models under unstable GPS condition. Seisan Kenkyu 65(2):91\u201395","journal-title":"Seisan Kenkyu"},{"issue":"2","key":"17817_CR30","first-page":"101","volume":"66","author":"A Kumar","year":"2014","unstructured":"Kumar A, Sato Y, Oishi T et al (2014) Improving gps position accuracy by identification of reflected gps signals using range data for modeling of urban structures. Seisan Kenkyu 66(2):101\u2013107","journal-title":"Seisan Kenkyu"},{"key":"17817_CR31","first-page":"14","volume":"1","author":"A Kumar","year":"2006","unstructured":"Kumar A (2006) Near-infrared optical imaging of the breast. Int J CARS 1:14\u201316","journal-title":"Int J CARS"},{"key":"17817_CR32","unstructured":"Ashwani K (2015) A hybrid approach to gps improvement in urban canyons. Int J Eng Sci Res Technol 1\u20136"},{"key":"17817_CR33","doi-asserted-by":"crossref","unstructured":"Zhang H, Cisse M, Dauphin Y et al (2017) Mixup: beyond empirical risk minimization. arXiv:1710.09412","DOI":"10.1007\/978-1-4899-7687-1_79"},{"issue":"9","key":"17817_CR34","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 et al (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17817_CR35","doi-asserted-by":"crossref","unstructured":"Liu S, Huang D (2018) Receptive field block net for accurate and fast object detection. Proceedings of the European conference on computer vision (ECCV), pp 385\u2013400","DOI":"10.1007\/978-3-030-01252-6_24"},{"issue":"4","key":"17817_CR36","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2017","unstructured":"Chen L, Papandreou G, Kokkinos I et al (2017) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17817_CR37","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J et al (2018) Cbam: convolutional block attention module. Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"17817_CR38","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze\u2013and\u2013excitation networks. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"5","key":"17817_CR39","doi-asserted-by":"publisher","first-page":"4099","DOI":"10.1109\/TITS.2020.3041278","volume":"23","author":"D Tian","year":"2020","unstructured":"Tian D, Lin C, Zhou J et al (2020) SA-YOLOv3: an efficient and accurate object detector using self-attention mechanism for autonomous driving. IEEE Trans Intell Transp Syst 23(5):4099\u20134110","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"17817_CR40","unstructured":"Chopra J, Kumar A, Aggarwal A et al (2016) Biometric system security issues and challenges. ICITEE2, pp 84\u201387"},{"key":"17817_CR41","first-page":"199","volume":"10","author":"D Maini","year":"2018","unstructured":"Maini D, Ashwani K (2018) Camera position estimation using 2D image dataset. Int J Innov Eng Technol 10:199\u2013203","journal-title":"Int J Innov Eng Technol"},{"issue":"5","key":"17817_CR42","first-page":"1","volume":"3","author":"A Aggarwal","year":"2015","unstructured":"Aggarwal A (2015) Autonomous navigation of intelligent vehicles using vision based method. Int J Res Electron Commun Technol 3(5):1\u201310","journal-title":"Int J Res Electron Commun Technol"},{"issue":"4","key":"17817_CR43","doi-asserted-by":"publisher","first-page":"366","DOI":"10.7763\/IJFCC.2012.V1.97","volume":"1","author":"S Rani","year":"2012","unstructured":"Rani S, Rajani N, Reddy S (2012) Comparative study on content based image retrieval. Int J Future Comput Commun 1(4):366","journal-title":"Int J Future Comput Commun"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17817-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17817-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17817-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T06:33:40Z","timestamp":1716618820000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17817-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,18]]},"references-count":43,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["17817"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17817-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,12,18]]},"assertion":[{"value":"25 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare that they have no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}