{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:56:24Z","timestamp":1779382584560,"version":"3.53.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,3,7]],"date-time":"2023-03-07T00:00:00Z","timestamp":1678147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,7]],"date-time":"2023-03-07T00:00:00Z","timestamp":1678147200000},"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":["51905416"],"award-info":[{"award-number":["51905416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51804249"],"award-info":[{"award-number":["51804249"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["2021JQ-572"],"award-info":[{"award-number":["2021JQ-572"]}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["2021JQ-574"],"award-info":[{"award-number":["2021JQ-574"]}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["5180425"],"award-info":[{"award-number":["5180425"]}]},{"name":"Qin Chuangyuan \u201cScientists + Engineers\u201d Team Construction Program in Shaanxi Province","award":["2022KXJ-38"],"award-info":[{"award-number":["2022KXJ-38"]}]},{"DOI":"10.13039\/501100013101","name":"Scientific Research Plan Projects of Shaanxi Education Department","doi-asserted-by":"publisher","award":["20JK0758"],"award-info":[{"award-number":["20JK0758"]}],"id":[{"id":"10.13039\/501100013101","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s00371-023-02789-y","type":"journal-article","created":{"date-parts":[[2023,3,7]],"date-time":"2023-03-07T09:02:56Z","timestamp":1678179776000},"page":"393-406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Hybrid dilated multilayer faster RCNN for object detection"],"prefix":"10.1007","volume":"40","author":[{"given":"Fangfang","family":"Xin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huipeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongguang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,7]]},"reference":[{"issue":"1","key":"2789_CR1","first-page":"115","volume":"10","author":"J Ren","year":"2022","unstructured":"Ren, J., Wang, Y.: Overview of object detection algorithms using convolutional neural networks. J. Comput. Commun. 10(1), 115\u2013132 (2022)","journal-title":"J. Comput. Commun."},{"key":"2789_CR2","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.613","volume":"7","author":"W Zheng","year":"2021","unstructured":"Zheng, W., Liu, X., Yin, L.: Research on image classification method based on improved multi-scale relational network. Peer J. Comput. Sci. 7, e613 (2021)","journal-title":"Peer J. Comput. Sci."},{"issue":"2","key":"2789_CR3","doi-asserted-by":"publisher","first-page":"100","DOI":"10.36548\/jiip.2021.2.003","volume":"3","author":"M Tripathi","year":"2021","unstructured":"Tripathi, M.: Analysis of convolutional neural network based image classification techniques. J. Innov. Image Process. 3(2), 100\u2013117 (2021)","journal-title":"J. Innov. Image Process."},{"key":"2789_CR4","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.future.2021.04.019","volume":"123","author":"D Jiang","year":"2021","unstructured":"Jiang, D., Li, G., Tan, C., et al.: Semantic segmentation for multiscale target based on object recognition using the improved Faster-RCNN model. Future Gener. Comput. Syst. 123, 94\u2013104 (2021)","journal-title":"Future Gener. Comput. Syst."},{"key":"2789_CR5","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6881-6890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"2789_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.fuel.2021.120475","volume":"294","author":"M Lei","year":"2021","unstructured":"Lei, M., Rao, Z., Wang, H., et al.: Maceral groups analysis of coal based on semantic segmentation of photomicrographs via the improved U-net. Fuel 294, 120475 (2021)","journal-title":"Fuel"},{"key":"2789_CR7","doi-asserted-by":"crossref","unstructured":"Liu Z., Hu H., Lin Y., et al.: Swin transformer v2: Scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009-12019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"2789_CR8","doi-asserted-by":"crossref","unstructured":"Fan H., Xiong B., Mangalam K., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824-6835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"2789_CR9","unstructured":"Zhang H., Li F., Liu S., et al.: Dino: detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"issue":"11","key":"2789_CR10","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"20","author":"ZQ Zhao","year":"2019","unstructured":"Zhao, Z.Q., Zheng, P., Xu, S., et al.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 20(11), 3212\u20133232 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2789_CR11","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2020.01.085","volume":"396","author":"X Wu","year":"2020","unstructured":"Wu, X., Sahoo, D., Hoi, S.C.H.: Recent advances in deep learning for object detection. Neurocomputing 396, 39\u201364 (2020)","journal-title":"Neurocomputing"},{"key":"2789_CR12","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, E., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"2789_CR13","first-page":"396","volume":"2","author":"Y Lecun","year":"1990","unstructured":"Lecun, Y., Boser, B., Denker, J.: Handwritten digit recognition with a back-propagation network. Adv. Neural Inf. Process. Syst. 2, 396\u2013404 (1990)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2789_CR14","doi-asserted-by":"crossref","unstructured":"Girshick R., Donahue J., Darrell T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580-587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"5","key":"2789_CR15","first-page":"1","volume":"13","author":"MA Chandra","year":"2021","unstructured":"Chandra, M.A., Bedi, S.S.: Survey on SVM and their application in image classification. Int. J. Inf. Technol. 13(5), 1\u201311 (2021)","journal-title":"Int. J. Inf. Technol."},{"issue":"9","key":"2789_CR16","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"KM He","year":"2014","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2789_CR17","doi-asserted-by":"crossref","unstructured":"Girshick R.: Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp. 1440-1448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"2789_CR18","unstructured":"Ren S., He K., Girshick R, et al.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"2789_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104229","volume":"112","author":"RF Mansour","year":"2021","unstructured":"Mansour, R.F., Escorcia-Gutierrez, J., Gamarra, M., et al.: Intelligent video anomaly detection and classification using faster RCNN with deep reinforcement learning model. Image Vis. Comput. 112, 104229 (2021)","journal-title":"Image Vis. Comput."},{"issue":"9","key":"2789_CR20","doi-asserted-by":"publisher","first-page":"8509","DOI":"10.1007\/s13369-021-05471-4","volume":"46","author":"S Albahli","year":"2021","unstructured":"Albahli, S., Nawaz, M., Javed, A., et al.: An improved faster-RCNN model for handwritten character recognition. Arab. J. Sci. Eng. 46(9), 8509\u20138523 (2021)","journal-title":"Arab. J. Sci. Eng."},{"key":"2789_CR21","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 472-480 (2017)","DOI":"10.1109\/CVPR.2017.75"},{"key":"2789_CR22","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.neunet.2021.03.013","volume":"141","author":"Z Zhao","year":"2021","unstructured":"Zhao, Z., Li, Q., Zhang, Z., et al.: Combining a parallel 2D CNN with a self-attention Dilated Residual Network for CTC-based discrete speech emotion recognition. Neural Netw. 141, 52\u201360 (2021)","journal-title":"Neural Netw."},{"key":"2789_CR23","doi-asserted-by":"crossref","unstructured":"Wang P., Chen P., Yuan Y., et al.: Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1451-1460 (2018)","DOI":"10.1109\/WACV.2018.00163"},{"key":"2789_CR24","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.neucom.2020.03.073","volume":"402","author":"X Jiang","year":"2020","unstructured":"Jiang, X., Wang, N., Xin, J., et al.: Image super-resolution via multi-view information fusion networks. Neurocomputing 402, 29\u201337 (2020)","journal-title":"Neurocomputing"},{"key":"2789_CR25","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.neunet.2021.08.002","volume":"144","author":"X Jiang","year":"2021","unstructured":"Jiang, X., Wang, N., Xin, J., et al.: Learning lightweight super-resolution networks with weight pruning. Neural Netw. 144, 21\u201332 (2021)","journal-title":"Neural Netw."},{"key":"2789_CR26","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.neucom.2020.12.076","volume":"432","author":"H Li","year":"2021","unstructured":"Li, H., Wang, N., Yu, Y., et al.: LBAN-IL: a novel method of high discriminative representation for facial expression recognition. Neurocomputing 432, 159\u2013169 (2021)","journal-title":"Neurocomputing"},{"key":"2789_CR27","doi-asserted-by":"publisher","first-page":"2016","DOI":"10.1109\/TIP.2021.3049955","volume":"30","author":"H Li","year":"2021","unstructured":"Li, H., Wang, N., Ding, X., et al.: Adaptively learning facial expression representation via cf labels and distillation. IEEE Trans. Image Process. 30, 2016\u20132028 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"2789_CR28","doi-asserted-by":"crossref","unstructured":"Zeiler M.D., Krishnan D., Taylor G.W., et al.: Deconvolutional networks. In: Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recongnition, pp. 25528-2535, San Francisco, CA, USA(2010)","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"2789_CR29","doi-asserted-by":"crossref","unstructured":"Cheng B. W., Xiao B., Wang J. D., Shi H. H.: HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5386-5395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"issue":"6","key":"2789_CR30","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.1007\/s11771-021-4731-9","volume":"28","author":"CH Xu","year":"2021","unstructured":"Xu, C.H., Shi, C., Chen, Y.N.: End-to-end dilated convolution network for document image semantic segmentation. J. Cent. South Univ. 28(6), 1765\u20131774 (2021)","journal-title":"J. Cent. South Univ."},{"key":"2789_CR31","unstructured":"Yu F., Koltun V.: Multi-Scale Context Aggregation by Dilated Convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"2789_CR32","doi-asserted-by":"crossref","unstructured":"Xiao B., Wu H., Wei Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision, pp. 466-481 (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"2789_CR33","doi-asserted-by":"crossref","unstructured":"Lin T. Y., Maire M., Belongie S., et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision. pp. 740-755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2789_CR34","doi-asserted-by":"crossref","unstructured":"Mansour, R.F., Escorcia-Gutierrez, J., Gamarra, M., et al.: Intelligent video anomaly detection and classification using faster RCNN with deep reinforcement learning model. Image Vis. Comput. 112, 104229 (2021)","DOI":"10.1016\/j.imavis.2021.104229"},{"key":"2789_CR35","doi-asserted-by":"crossref","unstructured":"Qiao L., Zhao Y., Li Z., et al.: Defrcn: Decoupled faster r-cnn for few-shot object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8681-8690 (2021)","DOI":"10.1109\/ICCV48922.2021.00856"},{"issue":"9","key":"2789_CR36","doi-asserted-by":"publisher","first-page":"8509","DOI":"10.1007\/s13369-021-05471-4","volume":"46","author":"S Albahli","year":"2021","unstructured":"Albahli, S., Nawaz, M., Javed, A., et al.: An improved faster-RCNN model for handwritten character recognition. Arab. J. Sci. Eng. 46(9), 8509\u20138523 (2021)","journal-title":"Arab. J. Sci. Eng."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02789-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02789-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02789-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,21]],"date-time":"2024-01-21T13:05:45Z","timestamp":1705842345000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02789-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,7]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["2789"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02789-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,7]]},"assertion":[{"value":"20 January 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}