{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:44:28Z","timestamp":1783097068112,"version":"3.54.6"},"reference-count":231,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000},"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":["No. 61806206"],"award-info":[{"award-number":["No. 61806206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["No. BK20180639"],"award-info":[{"award-number":["No. BK20180639"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20201346"],"award-info":[{"award-number":["BK20201346"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010014","name":"Six Talent Peaks Project in Jiangsu Province","doi-asserted-by":"publisher","award":["No. 2015-DZXX-010"],"award-info":[{"award-number":["No. 2015-DZXX-010"]}],"id":[{"id":"10.13039\/501100010014","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010014","name":"Six Talent Peaks Project in Jiangsu Province","doi-asserted-by":"publisher","award":["62172417"],"award-info":[{"award-number":["62172417"]}],"id":[{"id":"10.13039\/501100010014","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010014","name":"Six Talent Peaks Project in Jiangsu Province","doi-asserted-by":"publisher","award":["2018-XYDXX-044"],"award-info":[{"award-number":["2018-XYDXX-044"]}],"id":[{"id":"10.13039\/501100010014","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11042-023-15608-2","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T07:03:03Z","timestamp":1687244583000},"page":"10167-10209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Efficient convolutional neural networks and network compression methods for object detection: a survey"],"prefix":"10.1007","volume":"83","author":[{"given":"Yong","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3564-5090","authenticated-orcid":false,"given":"Jiaqi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,20]]},"reference":[{"key":"15608_CR1","unstructured":"Agarwal S, Du\u00a0Terrail JO, Jurie F (2018) Recent advances in object detection in the age of deep convolutional neural networks. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"issue":"8","key":"15608_CR2","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1016\/j.cviu.2013.04.005","volume":"117","author":"A Andreopoulos","year":"2013","unstructured":"Andreopoulos A, Tsotsos JK (2013) 50 years of object recognition: Directions forward. Comput Vis Image Underst 117(8):827\u2013891","journal-title":"Comput Vis Image Underst"},{"key":"15608_CR3","unstructured":"Ba LJ, Caruana R (2014) Do deep nets really need to be deep? In: Proceedings of the 27th international conference on neural information processing systems, vol 2, MIT Press, Cambridge, NIPS\u201914, pp 2654\u20132662"},{"key":"15608_CR4","doi-asserted-by":"crossref","unstructured":"Behrendt K, Novak L, Botros R (2017) A deep learning approach to traffic lights: detection, tracking, and classification. In: 2017 IEEE International conference on robotics and automation (ICRA), pp 1370\u20131377","DOI":"10.1109\/ICRA.2017.7989163"},{"key":"15608_CR5","doi-asserted-by":"crossref","unstructured":"Benenson R, Mathias M, Timofte R, Gool LV (2012) Pedestrian detection at 100 frames per second. In: Computer vision and pattern recognition (CVPR), 2012 IEEE Conference on","DOI":"10.1109\/CVPR.2012.6248017"},{"key":"15608_CR6","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection. ArXiv abs\/2004.10934"},{"issue":"8","key":"15608_CR7","doi-asserted-by":"crossref","first-page":"1844","DOI":"10.1109\/TPAMI.2019.2897684","volume":"41","author":"M Braun","year":"2019","unstructured":"Braun M, Krebs S, Flohr F, Gavrila DM (2019) Eurocity persons: a novel benchmark for person detection in traffic scenes. IEEE Trans Pattern Anal Mach Intell 41(8):1844\u20131861","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15608_CR8","doi-asserted-by":"publisher","unstructured":"Buciluundefined C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining, association for computing machinery, New York, NY, USA, KDD \u201906, pp 535\u2013541, https:\/\/doi.org\/10.1145\/1150402.1150464, https:\/\/doi.org\/10.1145\/1150402.1150464","DOI":"10.1145\/1150402.1150464"},{"key":"15608_CR9","unstructured":"Cai H, Zhu L, Han S (2019) ProxylessNAS: direct neural architecture search on target task and hardware. In: International conference on learning representations, https:\/\/arxiv.org\/pdf\/1812.00332.pdf"},{"key":"15608_CR10","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision, Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"15608_CR11","unstructured":"Chen G, Choi W, Yu X, Han T, Chandraker M (2017) Learning efficient object detection models with knowledge distillation. In: Proceedings of the 31st International conference on neural information processing systems, Curran Associates Inc., Red Hook, NIPS\u201917, pp 742\u2013751"},{"issue":"4","key":"15608_CR12","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2018","unstructured":"Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) 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":"15608_CR13","doi-asserted-by":"crossref","unstructured":"Chen L, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"15608_CR14","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2016) Multi-view 3d object detection network for autonomous driving. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2016.236"},{"key":"15608_CR15","unstructured":"Chen Y, Yang T, Zhang X, Meng G, Xiao X, Sun J (2019) Detnas: Backbone search for object detection. In: NeurIPS"},{"key":"15608_CR16","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","volume":"117","author":"G Cheng","year":"2016","unstructured":"Cheng G, Han J (2016) A survey on object detection in optical remote sensing images. ISPRS J Photogramm Remote Sens 117:11\u201328","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"15608_CR17","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","volume":"117","author":"G Cheng","year":"2016","unstructured":"Cheng G, Han J (2016) A survey on object detection in optical remote sensing images. ISPRS J Photogramm Remote Sens 117:11\u201328. https:\/\/doi.org\/10.1016\/j.isprsjprs.2016.03.014","journal-title":"ISPRS J Photogramm Remote Sens"},{"issue":"98","key":"15608_CR18","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.isprsjprs.2014.10.002","volume":"98","author":"G Cheng","year":"2014","unstructured":"Cheng G, Han J, Zhou P, Guo L (2014) Multi-class geospatial object detection and geographic image classification based on collection of part detectors. ISPRS J Photogramm Remote Sens 98(98):119\u2013132","journal-title":"ISPRS J Photogramm Remote Sens"},{"issue":"12","key":"15608_CR19","doi-asserted-by":"crossref","first-page":"7405","DOI":"10.1109\/TGRS.2016.2601622","volume":"54","author":"G Cheng","year":"2016","unstructured":"Cheng G, Zhou P, Han J (2016) Learning rotation-invariant convolutional neural networks for object detection in vhr optical remote sensing images. IEEE Trans Geosci Remote Sens 54(12):7405\u20137415","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"1","key":"15608_CR20","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1109\/TIP.2018.2867198","volume":"28","author":"G Cheng","year":"2019","unstructured":"Cheng G, Han J, Zhou P, Xu D (2019) Learning rotation-invariant and fisher discriminative convolutional neural networks for object detection. IEEE Trans Image Process 28(1):265\u2013278","journal-title":"IEEE Trans Image Process"},{"key":"15608_CR21","unstructured":"Cheng Y, Wang D, Zhou P, Zhang T (2017) A survey of model compression and acceleration for deep neural networks. CoRR abs\/1710.09282, http:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1710.html#abs-1710-09282"},{"issue":"1","key":"15608_CR22","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1109\/MSP.2017.2765695","volume":"35","author":"Y Cheng","year":"2018","unstructured":"Cheng Y, Wang D, Zhou P, Zhang T (2018) Model compression and acceleration for deep neural networks: the principles, progress, and challenges. IEEE Signal Process Mag 35(1):126\u2013136","journal-title":"IEEE Signal Process Mag"},{"key":"15608_CR23","doi-asserted-by":"crossref","unstructured":"Chollet F (2016) Xception: Deep learning with depthwise separable convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp 1800\u20131807","DOI":"10.1109\/CVPR.2017.195"},{"key":"15608_CR24","unstructured":"Chu X, Zhang B, Xu R, Ma H (2019) Multi-objective reinforced evolution in mobile neural architecture search. ArXiv abs\/1901.01074"},{"key":"15608_CR25","unstructured":"Courbariaux M, Bengio Y, David JP (2015) Binaryconnect: Training deep neural networks with binary weights during propagations. NIPS 28"},{"key":"15608_CR26","unstructured":"Courbariaux M, Hubara I, Soudry D, Elyaniv R, Bengio Y (2016) Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv$$:$$ Learning"},{"key":"15608_CR27","doi-asserted-by":"crossref","unstructured":"Dai J, He K, Sun J (2015) Instance-aware semantic segmentation via multi-task network cascades. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2016.343"},{"key":"15608_CR28","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), vol\u00a01, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"15608_CR29","doi-asserted-by":"crossref","unstructured":"de\u00a0Charette R, Nashashibi F (2009) Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates. In: 2009 IEEE Intelligent Vehicles Symposium, pp 358\u2013363","DOI":"10.1109\/IVS.2009.5164304"},{"key":"15608_CR30","doi-asserted-by":"publisher","unstructured":"Dollar P, Tu Z, Perona P, Belongie S (2009) Integral channel features. In: Proceedings of the British Machine Vision Conference, BMVA Press, pp 91.1\u201391.11, https:\/\/doi.org\/10.5244\/C.23.91","DOI":"10.5244\/C.23.91"},{"key":"15608_CR31","doi-asserted-by":"crossref","unstructured":"Dollar P, Wojek C, Schiele B, Perona P (2009) Pedestrian detection: a benchmark. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp 304\u2013311","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"15608_CR32","doi-asserted-by":"crossref","unstructured":"Dollar P, Wojek C, Schiele B, Perona P (2012) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34(4):743\u2013761","DOI":"10.1109\/TPAMI.2011.155"},{"issue":"8","key":"15608_CR33","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"P Dollar","year":"2014","unstructured":"Dollar P, Appel R, Belongie S, Perona P (2014) Fast feature pyramids for object detection. IEEE Trans Pattern Anal Mach Intell 36(8):1532\u20131545","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15608_CR34","doi-asserted-by":"crossref","unstructured":"Dong X, Yang Y (2019) One-shot neural architecture search via self-evaluated template network. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) pp 3680\u20133689","DOI":"10.1109\/ICCV.2019.00378"},{"key":"15608_CR35","doi-asserted-by":"publisher","unstructured":"Du Y, Xu C, Tao D (2017) Privileged matrix factorization for collaborative filtering. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, pp 1610\u20131616, https:\/\/doi.org\/10.24963\/ijcai.2017\/223, https:\/\/doi.org\/10.24963\/ijcai.2017\/223","DOI":"10.24963\/ijcai.2017\/223"},{"key":"15608_CR36","doi-asserted-by":"crossref","unstructured":"Dubout C, Fleuret F (2012) Exact acceleration of linear object detectors. In: In ECCV, 2012. 7","DOI":"10.1007\/978-3-642-33712-3_22"},{"key":"15608_CR37","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing S, Uchibe E, Doya K (2018) Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Networks: The Official Journal of the International Neural Network Society 107:3\u201311","journal-title":"Neural Networks: The Official Journal of the International Neural Network Society"},{"key":"15608_CR38","unstructured":"Eon PS, Simard PY, Haffner P, Lecun Y (1999) Boxlets: a fast convolution algorithm for signal processing and neural networks. In: Advances in Neural Information Processing Systems, MIT Press, pp 571\u2013577"},{"issue":"2","key":"15608_CR39","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, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303\u2013338. https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int J Comput Vis"},{"key":"15608_CR40","doi-asserted-by":"publisher","unstructured":"Everingham M, Eslami S, Van Gool L, Williams C, Winn J, Zisserman A (2014) The Pascal visual object classes challenge: a retrospective. Int J Comput Vis 111. https:\/\/doi.org\/10.1007\/s11263-014-0733-5","DOI":"10.1007\/s11263-014-0733-5"},{"key":"15608_CR41","first-page":"1871","volume":"9","author":"R Fan","year":"2008","unstructured":"Fan R, Chang K, Hsieh C, Wang X, Lin C (2008) Liblinear: A library for large linear classification. J Mach Learn Res 9:1871\u20131874","journal-title":"J Mach Learn Res"},{"key":"15608_CR42","unstructured":"Fan Y, Choi W, Lin Y (2016) Exploit all the layers: fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"15608_CR43","doi-asserted-by":"publisher","unstructured":"Felzenszwalb P, Mcallester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. vol\u00a08, https:\/\/doi.org\/10.1109\/CVPR.2008.4587597","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"15608_CR44","doi-asserted-by":"crossref","unstructured":"Felzenszwalb PF, Girshick RB (2012) From rigid templates to grammars: object detection with structured models","DOI":"10.1109\/ICCVW.2011.6130311"},{"key":"15608_CR45","doi-asserted-by":"crossref","unstructured":"Felzenszwalb PF, Girshick RB, McAllester D (2010a) Cascade object detection with deformable part models. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 2241\u20132248","DOI":"10.1109\/CVPR.2010.5539906"},{"issue":"9","key":"15608_CR46","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627\u20131645","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1\u20132","key":"15608_CR47","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1023\/A:1011113216584","volume":"41","author":"F Fleuret","year":"2001","unstructured":"Fleuret F, Geman D (2001) Coarse-to-fine face detection. Int J Comput Vis 41(1\u20132):85\u2013107","journal-title":"Int J Comput Vis"},{"key":"15608_CR48","unstructured":"Frankle J, Carbin M (2019) The lottery ticket hypothesis: finding sparse, trainable neural networks. arXiv$$:$$ Learning"},{"key":"15608_CR49","unstructured":"Gale T, Elsen E, Hooker S (2019) The state of sparsity in deep neural networks. arXiv$$:$$ Learning"},{"key":"15608_CR50","doi-asserted-by":"crossref","unstructured":"Gao M, Yu R, Li A, Morariu VI, Davis LS (2017) Dynamic zoom-in network for fast object detection in large images. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2018.00724"},{"key":"15608_CR51","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430"},{"key":"15608_CR52","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"15608_CR53","doi-asserted-by":"publisher","unstructured":"Gerards MET, Kuper J (2013) Optimal dpm and dvfs for frame-based real-time systems. ACM Trans Archit Code Optim 9(4), https:\/\/doi.org\/10.1145\/2400682.2400700, https:\/\/doi.org\/10.1145\/2400682.2400700","DOI":"10.1145\/2400682.2400700"},{"key":"15608_CR54","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin T, Pang R, Le QV (2019) Nas-fpn: learning scalable feature pyramid architecture for object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2019.00720"},{"key":"15608_CR55","doi-asserted-by":"crossref","unstructured":"Ghodrati A, Diba A, Pedersoli M, Tuytelaars T, Van\u00a0Gool L (2015) Deepproposal: hunting objects by cascading deep convolutional layers. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/ICCV.2015.296"},{"key":"15608_CR56","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. Computer Science","DOI":"10.1109\/ICCV.2015.169"},{"key":"15608_CR57","unstructured":"Girshick RB, Felzenszwalb PF, McAllester D (2011) Object detection with grammar models. In: Proceedings of the 24th International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NIPS\u201911, pp 442\u2013450"},{"key":"15608_CR58","doi-asserted-by":"crossref","unstructured":"Girshick RB, Donahue J, Darrell T, Malik J (2013) Rich feature hierarchies for accurate object detection and semantic segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"15608_CR59","unstructured":"Guo Y, Yao A, Chen Y (2016) Dynamic network surgery for efficient dnns. arXiv$$:$$ Neural and Evolutionary Computing"},{"key":"15608_CR60","unstructured":"Gupta S, Agrawal A, Gopalakrishnan K, Narayanan P (2015) Deep learning with limited numerical precision. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, vol 37, JMLR.org, ICML\u201915, pp 1737\u20131746"},{"key":"15608_CR61","doi-asserted-by":"crossref","unstructured":"Han J, Zhang D, Cheng G, Guo L, Ren J (2015) Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning. IEEE Trans Geosci Remote Sens 53(6):3325\u20133337","DOI":"10.1109\/TGRS.2014.2374218"},{"key":"15608_CR62","doi-asserted-by":"crossref","unstructured":"Han K, Wang Y, Tian Q, Guo J, Xu C, Xu C (2019) Ghostnet: more features from cheap operations. ArXiv abs\/1911.11907","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"15608_CR63","doi-asserted-by":"crossref","unstructured":"Han K, Wang Y, Tian Q, Guo J, Xu C, Xu C (2020) Ghostnet: more features from cheap operations. In: CVPR","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"15608_CR64","unstructured":"Han S, Mao H, Dally WJ (2015a) Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. CoRR abs\/1510.00149"},{"key":"15608_CR65","unstructured":"Han S, Mao H, Dally WJ (2015b) Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"key":"15608_CR66","doi-asserted-by":"crossref","unstructured":"Han S, Liu X, Mao H, Pu J, Pedram A, Horowitz MA, Dally WJ (2016) Eie: efficient inference engine on compressed deep neural network. In: 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), pp 243\u2013254","DOI":"10.1109\/ISCA.2016.30"},{"key":"15608_CR67","first-page":"177","volume-title":"Comparing biases for minimal network construction with back-propagation","author":"SJ Hanson","year":"1989","unstructured":"Hanson SJ, Pratt L (1989) Comparing biases for minimal network construction with back-propagation. Morgan Kaufmann Publishers Inc., San Francisco, pp 177\u2013185"},{"key":"15608_CR68","doi-asserted-by":"crossref","unstructured":"Hariharan B, Arbelaez P, Girshick R, Malik J (2014) Simultaneous detection and segmentation. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"15608_CR69","unstructured":"Hassibi B, GStork D (1992) Second order derivatives for network pruning: optimal brain surgeon. Adv Neural Inform Proc Syst 5"},{"key":"15608_CR70","unstructured":"Haussler D (2001) Convolution kernels on discrete structures ucsc-crl-99-10"},{"key":"15608_CR71","doi-asserted-by":"crossref","unstructured":"He K, Sun J (2014) Convolutional neural networks at constrained time cost. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5353\u20135360","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"15608_CR72","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2014","unstructured":"He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37:1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15608_CR73","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"15608_CR74","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"15608_CR75","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He K, Gkioxari G, Dollar P, Girshick R (2020) Mask R-CNN. IEEE Trans Pattern Anal Mach Intell 42(2):386\u2013397","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15608_CR76","doi-asserted-by":"crossref","unstructured":"He Y, Lin J, Liu Z, Wang H, Li L, Han S (2018) Amc: automl for model compression and acceleration on mobile devices. In: ECCV","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"15608_CR77","unstructured":"Hendrycks D, Gimpel K (2016) Bridging nonlinearities and stochastic regularizers with gaussian error linear units. CoRR abs\/1606.08415"},{"issue":"5786","key":"15608_CR78","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov R (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"key":"15608_CR79","unstructured":"Hinton GE, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv$$:$$ Machine Learning"},{"key":"15608_CR80","unstructured":"Hong S, Roh B, Kim K, Cheon Y, Park M (2016) Pvanet: lightweight deep neural networks for real-time object detection. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"key":"15608_CR81","doi-asserted-by":"crossref","unstructured":"Houben S, Stallkamp J, Salmen J, Schlipsing M, Igel C (2013) Detection of traffic signs in real-world images: the German traffic sign detection benchmark. In: International Joint Conference on Neural Networks, 1288","DOI":"10.1109\/IJCNN.2013.6706807"},{"key":"15608_CR82","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V, Le QV, Adam H (2019) Searching for mobilenetv3. ArXiv abs\/1905.02244","DOI":"10.1109\/ICCV.2019.00140"},{"key":"15608_CR83","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. ArXiv abs\/1704.04861"},{"key":"15608_CR84","unstructured":"Hsu CH, Chang SH, Juan DC, Pan JY, Chen YT, Wei W, Chang SC (2018) Monas: multi-objective neural architecture search using reinforcement learning. ArXiv abs\/1806.10332"},{"key":"15608_CR85","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Weinberger KQ (2016a) Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2261\u20132269","DOI":"10.1109\/CVPR.2017.243"},{"key":"15608_CR86","doi-asserted-by":"crossref","unstructured":"Huang G, Liu S, van\u00a0der Maaten L, Weinberger KQ (2017) Condensenet: an efficient densenet using learned group convolutions. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2752\u20132761","DOI":"10.1109\/CVPR.2018.00291"},{"key":"15608_CR87","doi-asserted-by":"crossref","unstructured":"Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, Fischer I, Wojna Z, Song Y, Guadarrama S, et\u00a0al. (2016b) Speed\/accuracy trade-offs for modern convolutional object detectors. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2017.351"},{"key":"15608_CR88","unstructured":"Iandola FN, Moskewicz MW, Ashraf K, Han S, Dally WJ, Keutzer K (2017) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and $$<$$1mb model size. ArXiv abs\/1602.07360"},{"key":"15608_CR89","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv$$:$$ Learning"},{"key":"15608_CR90","unstructured":"Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2014) Synthetic data and artificial neural networks for natural scene text recognition. In: Workshop on Deep Learning, NIPS"},{"key":"15608_CR91","unstructured":"Jain V, Learned-Miller E (2010) Fddb: a benchmark for face detection in unconstrained settings. Tech. Rep. UM-CS-2010-009, University of Massachusetts, Amherst"},{"key":"15608_CR92","doi-asserted-by":"crossref","unstructured":"Jiang B, Luo R, Mao J, Xiao T, Jiang Y (2018) Acquisition of localization confidence for accurate object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"15608_CR93","unstructured":"Jin X, Yuan XT, Feng J, Yan S (2016) Training skinny deep neural networks with iterative hard thresholding methods. ArXiv abs\/1607.05423"},{"issue":"7","key":"15608_CR94","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.1162\/089976603321891855","volume":"15","author":"SS Keerthi","year":"2003","unstructured":"Keerthi SS, Lin C (2003) Asymptotic behaviors of support vector machines with gaussian kernel. Neural Comput 15(7):1667\u20131689","journal-title":"Neural Comput"},{"key":"15608_CR95","doi-asserted-by":"crossref","unstructured":"Kokkinos I (2012) Bounding part scores for rapid detection with deformable part models. In: Proceedings of European Conference on Computer Vision","DOI":"10.1007\/978-3-642-33885-4_5"},{"key":"15608_CR96","doi-asserted-by":"crossref","unstructured":"Kong T, Yao A, Chen Y, Sun F (2016) Hypernet: towards accurate region proposal generation and joint object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2016.98"},{"key":"15608_CR97","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks pp 1097\u20131105"},{"key":"15608_CR98","doi-asserted-by":"crossref","unstructured":"K\u00f6stinger M, Wohlhart P, Roth PM, Bischof H (2011) Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: 2011 IEEE International Conference on Computer Vision orkshops (ICCV Workshops), pp 2144\u20132151","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"15608_CR99","unstructured":"Lam D, Kuzma R, Mcgee K, Dooley S, Laielli M, Klaric MN, Bulatov Y, Mccord B (2018) xview: objects in context in overhead imagery. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"issue":"12","key":"15608_CR100","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1109\/TPAMI.2009.144","volume":"31","author":"CH Lampert","year":"2009","unstructured":"Lampert CH, Blaschko MB, Hofmann T (2009) Efficient subwindow search: a branch and bound framework for object localization. IEEE Trans Pattern Anal Mach Intell 31(12):2129\u20132142","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"15608_CR101","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1007\/s11263-019-01204-1","volume":"128","author":"H Law","year":"2020","unstructured":"Law H, Deng J (2020) Cornernet: detecting objects as paired keypoints. Int J Comput Vis 128(3):642\u2013656","journal-title":"Int J Comput Vis"},{"key":"15608_CR102","doi-asserted-by":"crossref","unstructured":"Leather H, Bonilla E, O\u2019Boyle M (2009) Automatic feature generation for machine learning based optimizing compilation. In: 2009 International Symposium on Code Generation and Optimization, pp 81\u201391","DOI":"10.1109\/CGO.2009.21"},{"key":"15608_CR103","unstructured":"LeCun Y, Denker JS, Solla SA (1989) Optimal brain damage. In: NIPS"},{"issue":"11","key":"15608_CR104","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278\u20132324","journal-title":"Proceedings of the IEEE"},{"key":"15608_CR105","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86:2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proceedings of the IEEE"},{"issue":"11","key":"15608_CR106","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278\u20132324","journal-title":"Proceedings of the IEEE"},{"key":"15608_CR107","doi-asserted-by":"crossref","unstructured":"Li B, Wu B, Su J, Wang G, Lin L (2020a) Eagleeye: fast sub-net evaluation for efficient neural network pruning. arXiv:2007.02491","DOI":"10.1007\/978-3-030-58536-5_38"},{"key":"15608_CR108","doi-asserted-by":"crossref","unstructured":"Li H, Lin Z, Shen X, Brandt J, Hua G (2015) A convolutional neural network cascade for face detection. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5325\u20135334","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"15608_CR109","unstructured":"Li H, Kadav A, Durdanovic I, Samet H, Graf HP (2016) Pruning filters for efficient convnets. ArXiv abs\/1608.08710"},{"key":"15608_CR110","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.isprsjprs.2019.11.023","volume":"159","author":"K Li","year":"2020","unstructured":"Li K, Wan G, Cheng G, Meng L, Han J (2020) Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J Photogramm Remote Sens 159:296\u2013307","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"15608_CR111","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.isprsjprs.2019.11.023","volume":"159","author":"K Li","year":"2020","unstructured":"Li K, Wan G, Cheng G, Meng L, Han J (2020) Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J Photogramm Remote Sens 159:296\u2013307. https:\/\/doi.org\/10.1016\/j.isprsjprs.2019.11.023","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"15608_CR112","doi-asserted-by":"crossref","unstructured":"Li Q, Jin S, Yan J (2017) Mimicking very efficient network for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 7341\u20137349","DOI":"10.1109\/CVPR.2017.776"},{"key":"15608_CR113","doi-asserted-by":"crossref","unstructured":"Li Y, Lin S, Zhang B, Liu J, Doermann D, Wu Y, Huang F, Ji R (2018) Exploiting kernel sparsity and entropy for interpretable cnn compression. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2019.00291"},{"key":"15608_CR114","unstructured":"Li Z, Peng C, Yu G, Zhang X, Deng Y, Sun J (2017) Light-head r-cnn: in defense of two-stage object detector. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"key":"15608_CR115","doi-asserted-by":"crossref","unstructured":"Lin S, Ji R, Yan C, Zhang B, Cao L, Ye Q, Huang F, Doermann D (2019) Towards optimal structured cnn pruning via generative adversarial learning. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 2785\u20132794","DOI":"10.1109\/CVPR.2019.00290"},{"key":"15608_CR116","doi-asserted-by":"crossref","unstructured":"Lin T, Maire M, Belongie S, Bourdev L, Girshick R, Hays J, Perona P, Ramanan D, Zitnick CL, Dollar P (2014a) Microsoft coco: common objects in context. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"15608_CR117","doi-asserted-by":"crossref","unstructured":"Lin T, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2016) Feature pyramid networks for object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2017.106"},{"key":"15608_CR118","doi-asserted-by":"crossref","unstructured":"Lin T, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017a) Feature pyramid networks for object detection, pp 936\u2013944","DOI":"10.1109\/CVPR.2017.106"},{"key":"15608_CR119","doi-asserted-by":"crossref","unstructured":"Lin T, Goyal P, Girshick R, He K, Dollar P (2017b) Focal loss for dense object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/ICCV.2017.324"},{"key":"15608_CR120","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision - ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision - ECCV 2014. Springer International Publishing, Cham, pp 740\u2013755"},{"key":"15608_CR121","unstructured":"Lin X, Zhao C, Pan W (2017c) Towards accurate binary convolutional neural network. In: NIPS"},{"issue":"9","key":"15608_CR122","doi-asserted-by":"crossref","first-page":"1938","DOI":"10.1109\/LGRS.2015.2439517","volume":"12","author":"K Liu","year":"2015","unstructured":"Liu K, Mattyus G (2015) Fast multiclass vehicle detection on aerial images. IEEE Geosci Remote Sens Lett 12(9):1938\u20131942","journal-title":"IEEE Geosci Remote Sens Lett"},{"issue":"2","key":"15608_CR123","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu L, Ouyang W, Wang X, Fieguth P, Chen J, Liu X, Pietikainen M (2020) Deep learning for generic object detection: a survey. Int. J. Comput. Vis 128(2):261\u2013318","journal-title":"Int. J. Comput. Vis"},{"key":"15608_CR124","doi-asserted-by":"crossref","unstructured":"Liu S, Huang D, Wang Y (2017) Receptive field block net for accurate and fast object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"15608_CR125","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2018.00913"},{"key":"15608_CR126","unstructured":"Liu S, Huang D, Wang Y (2019a) Learning spatial fusion for single-shot object detection. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"key":"15608_CR127","unstructured":"Liu S, Ren B, Shen X, Wang Y (2020b) Cocopie: Making mobile ai sweet as pie -compression-compilation co-design goes a long way. ArXiv abs\/2003.06700"},{"issue":"1","key":"15608_CR128","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/TFUZZ.2020.3006520","volume":"29","author":"S Liu","year":"2020","unstructured":"Liu S, Wang S, Liu X, Lin CT, Lv Z (2020) Fuzzy detection aided real-time and robust visual tracking under complex environments. IEEE Trans Fuzzy Syst 29(1):90\u2013102","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"15608_CR129","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1109\/TMM.2021.3065580","volume":"23","author":"S Liu","year":"2021","unstructured":"Liu S, Wang S, Liu X, Gandomi AH, Daneshmand M, Muhammad K, De Albuquerque VHC (2021) Human memory update strategy: a multi-layer template update mechanism for remote visual monitoring. IEEE Trans Multimedia 23:2188\u20132198","journal-title":"IEEE Trans Multimedia"},{"key":"15608_CR130","doi-asserted-by":"crossref","unstructured":"Liu S, Wang S, Liu X, Dai J, Muhammad K, Gandomi AH, Ding W, Hijji M, de\u00a0Albuquerque VHC (2022) Human inertial thinking strategy: A novel fuzzy reasoning mechanism for iot-assisted visual monitoring. IEEE Internet Things J","DOI":"10.1109\/JIOT.2022.3142115"},{"key":"15608_CR131","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed SE, Fu CY, Berg AC (2016) Ssd: single shot multibox detector. In: ECCV","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"15608_CR132","doi-asserted-by":"crossref","unstructured":"Liu Z, Li J, Shen Z, Huang G, Yan S, Zhang C (2017) Learning efficient convolutional networks through network slimming. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp 2755\u20132763","DOI":"10.1109\/ICCV.2017.298"},{"key":"15608_CR133","unstructured":"Liu Z, Sun M, Zhou T, Huang G, Darrell T (2019b) Rethinking the value of network pruning. In: ICLR"},{"key":"15608_CR134","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2014) Fully convolutional networks for semantic segmentation. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"15608_CR135","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1109\/ICCV.1999.790410","volume":"2","author":"DG Lowe","year":"1999","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. Proceedings of the Seventh IEEE International Conference on Computer Vision 2:1150\u20131157","journal-title":"Proceedings of the Seventh IEEE International Conference on Computer Vision"},{"key":"15608_CR136","doi-asserted-by":"crossref","unstructured":"Lucas SM, Panaretos A, Sosa L, Tang A, Wong S, Young R (2003) Icdar 2003 robust reading competitions. In: Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings., pp 682\u2013687","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"15608_CR137","doi-asserted-by":"crossref","unstructured":"Luo JH, Wu J (2020) Autopruner: an end-to-end trainable filter pruning method for efficient deep model inference. ArXiv abs\/1805.08941","DOI":"10.1016\/j.patcog.2020.107461"},{"key":"15608_CR138","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng HT, Sun J (2018) Shufflenet v2: practical guidelines for efficient cnn architecture design. ArXiv abs\/1807.11164","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"15608_CR139","doi-asserted-by":"crossref","unstructured":"Maji S, Berg AC, Malik J (2008) Classification using intersection kernel support vector machines is efficient. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587630"},{"key":"15608_CR140","unstructured":"Malik J (2015) Hypercolumns for object segmentation and fine-grained localization. In: IEEE Conference on Computer Vision & Pattern Recognition"},{"key":"15608_CR141","unstructured":"Mathieu M, Henaff M, Lecun Y (2013) Fast training of convolutional networks through ffts. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"key":"15608_CR142","doi-asserted-by":"crossref","unstructured":"Mehrara H, Zahedinejad M, Pourmohammad A (2009) Novel edge detection using bp neural network based on threshold binarization. In: 2009 Second International Conference on Computer and Electrical Engineering, vol\u00a02, pp 408\u2013412","DOI":"10.1109\/ICCEE.2009.144"},{"issue":"4","key":"15608_CR143","doi-asserted-by":"crossref","first-page":"1484","DOI":"10.1109\/TITS.2012.2209421","volume":"13","author":"A Mogelmose","year":"2012","unstructured":"Mogelmose A, Trivedi MM, Moeslund TB (2012) Vision-based traffic sign detection and analysis for intelligent driver assistance systems: perspectives and survey. IEEE Trans Intell Transp Syst 13(4):1484\u20131497","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"15608_CR144","unstructured":"Mukkamala MC, Hein M (2017) Variants of rmsprop and adagrad with logarithmic regret bounds. arXiv$$:$$ Learning"},{"key":"15608_CR145","doi-asserted-by":"crossref","unstructured":"Nada H, Sindagi VA, Zhang H, Patel V (2018) Pushing the limits of unconstrained face detection: a challenge dataset and baseline results. 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS), pp 1\u201310","DOI":"10.1109\/BTAS.2018.8698561"},{"issue":"4","key":"15608_CR146","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1109\/TMM.2006.876287","volume":"8","author":"JC Nascimento","year":"2006","unstructured":"Nascimento JC, Marques JS (2006) Performance evaluation of object detection algorithms for video surveillance. IEEE Trans Multimedia 8(4):761\u2013774","journal-title":"IEEE Trans Multimedia"},{"key":"15608_CR147","doi-asserted-by":"crossref","unstructured":"Neubeck A, Gool LJV (2006) Efficient non-maximum suppression. In: International Conference on Pattern Recognition","DOI":"10.1109\/ICPR.2006.479"},{"key":"15608_CR148","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"15608_CR149","doi-asserted-by":"crossref","unstructured":"Noh H, Hong S, Han B (2015) Learning deconvolution network for semantic segmentation. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/ICCV.2015.178"},{"key":"15608_CR150","doi-asserted-by":"crossref","unstructured":"Oksuz K, Cam BC, Akbas E, Kalkan S (2018) Localization recall precision (lrp): a new performance metric for object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-030-01234-2_31"},{"key":"15608_CR151","doi-asserted-by":"crossref","unstructured":"Ouyang W, Wang K, Zhu X, Wang X (2017) Chained cascade network for object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp 1956\u20131964","DOI":"10.1109\/ICCV.2017.214"},{"key":"15608_CR152","unstructured":"Ouyang W, Wang K, Zhu X, Wang X (2017) Learning chained deep features and classifiers for cascade in object detection. ArXiv abs\/1702.07054"},{"issue":"1","key":"15608_CR153","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1023\/A:1008162616689","volume":"38","author":"C Papageorgiou","year":"2000","unstructured":"Papageorgiou C, Poggio T (2000) A trainable system for object detection. Int J Comput Vis 38(1):15\u201333","journal-title":"Int J Comput Vis"},{"key":"15608_CR154","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1023\/A:1008162616689","volume":"38","author":"C Papageorgiou","year":"2000","unstructured":"Papageorgiou C, Poggio T (2000) A trainable system for object detection. Int. J. Comput. Vis 38:15\u201333. https:\/\/doi.org\/10.1023\/A:1008162616689","journal-title":"Int. J. Comput. Vis"},{"key":"15608_CR155","unstructured":"Parmar N, Vaswani A, Uszkoreit J, Kaiser L, Shazeer N, Ku A, Tran D (2018) Image transformer. In: International Conference on Machine Learning, PMLR, pp 4055\u20134064"},{"key":"15608_CR156","doi-asserted-by":"crossref","unstructured":"Peng C, Zhang X, Yu G, Luo G, Sun J (2017) Large kernel matters - improve semantic segmentation by global convolutional network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1743\u20131751","DOI":"10.1109\/CVPR.2017.189"},{"key":"15608_CR157","doi-asserted-by":"crossref","unstructured":"Porikli F (2005) Integral histogram: a fast way to extract histograms in cartesian spaces. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol\u00a01, pp 829\u2013836 vol. 1","DOI":"10.1109\/CVPR.2005.188"},{"key":"15608_CR158","doi-asserted-by":"publisher","unstructured":"Pratt H, Williams B, Coenen F, Zheng Y (2017) FCNN: Fourier convolutional neural networks. In: Machine Learning and Knowledge Discovery in Databases, Springer International Publishing, pp 786\u2013798, https:\/\/doi.org\/10.1007\/978-3-319-71249-9_47, https:\/\/doi.org\/10.1007%2F978-3-319-71249-9_47","DOI":"10.1007\/978-3-319-71249-9_47"},{"key":"15608_CR159","unstructured":"Qiang Zhu, Mei-Chen Yeh, Kwang-Ting Cheng, Avidan S (2006) Fast human detection using a cascade of histograms of oriented gradients. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906), vol\u00a02, pp 1491\u20131498"},{"key":"15608_CR160","unstructured":"Ramachandran P, Zoph B, Le QV (2017) Swish: a self-gated activation function. arXiv$$:$$ Neural and Evolutionary Computing"},{"key":"15608_CR161","doi-asserted-by":"crossref","unstructured":"Rastegari M, Ordonez V, Redmon J, Farhadi A (2016a) Xnor-net: Imagenet classification using binary convolutional neural networks. In: ECCV","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"15608_CR162","doi-asserted-by":"crossref","unstructured":"Razakarivony S, Jurie F (2016) Vehicle detection in aerial imagery: a small target detection benchmark. J Vis Commun Image Represent 34(Jan.):187\u2013203","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"15608_CR163","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2016) Yolo9000: better, faster, stronger. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2017.690"},{"key":"15608_CR164","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"key":"15608_CR165","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala SK, Girshick RB, Farhadi A (2016) You only look once: unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"15608_CR166","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) 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":"7","key":"15608_CR167","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1109\/TPAMI.2016.2601099","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Zhang X, Sun J (2017) Object detection networks on convolutional feature maps. IEEE Trans Pattern Anal Mach Intell 39(7):1476\u20131481","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15608_CR168","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) Generalized intersection over union: a metric and a loss for bounding box regression. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2019.00075"},{"key":"15608_CR169","unstructured":"Rippel O, Snoek J, Adams RP (2015) Spectral representations for convolutional neural networks. ArXiv abs\/1506.03767"},{"key":"15608_CR170","unstructured":"Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y (2014) Fitnets: hints for thin deep nets. arXiv$$:$$ Learning"},{"key":"15608_CR171","first-page":"318","volume-title":"Learning internal representations by Error Propagation","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by Error Propagation. MIT Press, Cambridge, pp 318\u2013362"},{"issue":"3","key":"15608_CR172","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis (IJCV) 115(3):211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int J Comput Vis (IJCV)"},{"key":"15608_CR173","unstructured":"Sadeghi MA, Forsyth D (2013) Fast template evaluation with vector quantization. In: Advances in Neural Information Processing Systems (NIPS)"},{"key":"15608_CR174","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard AG, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: inverted residuals and linear bottlenecks. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"15608_CR175","doi-asserted-by":"crossref","unstructured":"Shang W, Sohn K, Almeida D, Lee H (2016) Understanding and improving convolutional neural networks via concatenated rectified linear units. In: ICML","DOI":"10.1609\/aaai.v31i1.10759"},{"issue":"4","key":"15608_CR176","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640\u2013651","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15608_CR177","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556"},{"key":"15608_CR178","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015a) Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"15608_CR179","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015b) Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"15608_CR180","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2016) Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"15608_CR181","doi-asserted-by":"crossref","unstructured":"Tan M, Chen B, Pang R, Vasudevan V, Le QV (2018) Mnasnet: platform-aware neural architecture search for mobile. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp 2815\u20132823","DOI":"10.1109\/CVPR.2019.00293"},{"key":"15608_CR182","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2019) Efficientdet: scalable and efficient object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"15608_CR183","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: fully convolutional one-stage object detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) pp 9626\u20139635","DOI":"10.1109\/ICCV.2019.00972"},{"issue":"3","key":"15608_CR184","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1109\/TPAMI.2018.2886192","volume":"42","author":"F Tung","year":"2020","unstructured":"Tung F, Mori G (2020) Deep neural network compression by in-parallel pruning-quantization. IEEE Trans Pattern Anal Mach Intell 42(3):568\u2013579","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15608_CR185","doi-asserted-by":"crossref","unstructured":"Tzelepis G, Asif A, Baci S, Cavdar S, Aksoy EE (2019) Deep neural network compression for image classification and object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/ICMLA.2019.00266"},{"issue":"4","key":"15608_CR186","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1049\/ip-vis:19941301","volume":"141","author":"R Vaillant","year":"1994","unstructured":"Vaillant R, Monrocq C, Le Cun Y (1994) Original approach for the localisation of objects in images. IEEE Proceedings-Vision, Image and Signal Processing 141(4):245","journal-title":"IEEE Proceedings-Vision, Image and Signal Processing"},{"key":"15608_CR187","unstructured":"Vanhoucke V, Senior A, Mao MZ (2011) Improving the speed of neural networks on cpus. In: in Deep Learning and Unsupervised Feature Learning Workshop, NIPS"},{"key":"15608_CR188","unstructured":"Vasilache N, Johnson J, Mathieu M, Chintala S, Piantino S, Lecun Y (2014) Fast convolutional nets with fbfft: a gpu performance evaluation. arXiv$$:$$ Learning"},{"key":"15608_CR189","doi-asserted-by":"crossref","unstructured":"Vedaldi A, Zisserman A (2012a) Sparse kernel approximations for efficient classification and detection. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp 2320\u20132327","DOI":"10.1109\/CVPR.2012.6247943"},{"key":"15608_CR190","doi-asserted-by":"publisher","unstructured":"Vedaldi A, Zisserman A (2012b) Sparse kernel approximations for efficient classification and detection. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, https:\/\/doi.org\/10.1109\/cvpr.2012.6247943, https:\/\/doi.org\/10.1109%2Fcvpr.2012.6247943","DOI":"10.1109\/cvpr.2012.6247943"},{"key":"15608_CR191","doi-asserted-by":"crossref","unstructured":"Vedaldi A, Gulshan V, Varma M, Zisserman A (2009) Multiple kernels for object detection. 2009 IEEE 12th International Conference on Computer Vision pp 606\u2013613","DOI":"10.1109\/ICCV.2009.5459183"},{"key":"15608_CR192","unstructured":"Veit A, Matera T, Neumann L, Matas J, Belongie SJ (2016) Coco-text: dataset and benchmark for text detection and recognition in natural images. ArXiv abs\/1601.07140"},{"key":"15608_CR193","doi-asserted-by":"crossref","unstructured":"Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol\u00a01, pp I\u2013I","DOI":"10.1109\/CVPR.2001.990517"},{"key":"15608_CR194","doi-asserted-by":"crossref","unstructured":"Violapaul, Jonesmichael J (2004) Robust real-time face detection. Int J Comput Vis","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"15608_CR195","doi-asserted-by":"crossref","unstructured":"Wang K, Babenko B, Belongie S (2011) End-to-end scene text recognition. In: 2011 International conference on computer vision, IEEE, pp 1457\u20131464","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"15608_CR196","doi-asserted-by":"crossref","unstructured":"Wang K, Liu Z, Lin Y, Lin J, Han S (2018) Haq: hardware-aware automated quantization. arXiv","DOI":"10.1109\/CVPR.2019.00881"},{"key":"15608_CR197","doi-asserted-by":"crossref","unstructured":"Wang X, Han TX, Yan S (2009) An hog-lbp human detector with partial occlusion handling. In: 2009 IEEE 12th International Conference on Computer Vision, pp 32\u201339","DOI":"10.1109\/ICCV.2009.5459207"},{"issue":"2","key":"15608_CR198","first-page":"39","volume":"2","author":"T Watanabe","year":"2010","unstructured":"Watanabe T, Ito S, Yokoi K (2010) Co-occurrence histograms of oriented gradients for human detection. J Inf Process Syst 2(2):39\u201347","journal-title":"J Inf Process Syst"},{"key":"15608_CR199","unstructured":"Wen W, Wu C, Wang Y, Chen Y, Li H (2016) Learning structured sparsity in deep neural networks. arXiv$$:$$ Neural and Evolutionary Computing"},{"issue":"4","key":"15608_CR200","first-page":"127","volume":"21","author":"P Wilson","year":"2006","unstructured":"Wilson P, Fernandez JD (2006) Facial feature detection using haar classifiers. J Comput Sci Coll 21(4):127\u2013133","journal-title":"J Comput Sci Coll"},{"key":"15608_CR201","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J, Kweon IS (2018) Cbam: convolutional block attention module. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"15608_CR202","doi-asserted-by":"crossref","unstructured":"Wu J, Leng C, Wang Y, Hu Q, Cheng J (2016) Quantized convolutional neural networks for mobile devices. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4820\u20134828","DOI":"10.1109\/CVPR.2016.521"},{"key":"15608_CR203","doi-asserted-by":"crossref","unstructured":"Xia G, Bai X, Ding J, Zhu Z, Belongie S, Luo J, Datcu M, Pelillo M, Zhang L (2017) Dota: a large-scale dataset for object detection in aerial images. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2018.00418"},{"key":"15608_CR204","unstructured":"Yang J (2015) Notes on low-rank matrix factorization. arXiv$$:$$ Numerical Analysis"},{"key":"15608_CR205","doi-asserted-by":"crossref","unstructured":"Yang S, Luo P, Loy CC, Tang X (2016) Wider face: a face detection benchmark. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5525\u20135533","DOI":"10.1109\/CVPR.2016.596"},{"key":"15608_CR206","doi-asserted-by":"crossref","unstructured":"Yang TJ, Howard AG, Chen B, Zhang X, Go A, Sze V, Adam H (2018) Netadapt: platform-aware neural network adaptation for mobile applications. In: ECCV","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"15608_CR207","unstructured":"Yao C, Bai X, Liu W, Ma Y, Tu Z (2012) Detecting texts of arbitrary orientations in natural images. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp 1083\u20131090"},{"key":"15608_CR208","unstructured":"Yu G, Chang Q, Lv W, Xu C, Cui C, Ji W, Dang Q, Deng K, Wang G, Du Y, et\u00a0al. (2021) Pp-picodet: a better real-time object detector on mobile devices. arXiv preprint arXiv:2111.00902"},{"key":"15608_CR209","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2013) Visualizing and understanding convolutional networks. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-319-10590-1_53"},{"issue":"10","key":"15608_CR210","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499\u20131503","journal-title":"IEEE Signal Process Lett"},{"key":"15608_CR211","doi-asserted-by":"crossref","unstructured":"Zhang L, Liang L, Liang X, He K (2016b) Is faster r-cnn doing well for pedestrian detection? In: European Conference on Computer Vision","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"15608_CR212","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2017a) Single-shot refinement neural network for object detection. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2018.00442"},{"key":"15608_CR213","doi-asserted-by":"crossref","unstructured":"Zhang T, Qi G, Xiao B, Wang J (2017b) Interleaved group convolutions for deep neural networks. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/ICCV.2017.469"},{"key":"15608_CR214","doi-asserted-by":"crossref","unstructured":"Zhang X, Zou J, Ming X, He K, Sun J (2014) Efficient and accurate approximations of nonlinear convolutional networks. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp 1984\u20131992","DOI":"10.1109\/CVPR.2015.7298809"},{"key":"15608_CR215","doi-asserted-by":"crossref","first-page":"1943","DOI":"10.1109\/TPAMI.2015.2502579","volume":"38","author":"X Zhang","year":"2015","unstructured":"Zhang X, Zou J, He K, Sun J (2015) Accelerating very deep convolutional networks for classification and detection. IEEE Trans Pattern Anal Mach Intell 38:1943\u20131955","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15608_CR216","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2017c) Shufflenet: an extremely efficient convolutional neural network for mobile devices. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2018.00716"},{"key":"15608_CR217","doi-asserted-by":"publisher","first-page":"755","DOI":"10.3390\/rs11070755","volume":"11","author":"X Zhang","year":"2019","unstructured":"Zhang X, Zhu K, Guanzhou C, Xiaoliang T, Zhang L, Dai F, Liao P, Gong Y (2019) Geospatial object detection on high resolution remote sensing imagery based on double multi-scale feature pyramid network. Remote Sens 11:755. https:\/\/doi.org\/10.3390\/rs11070755","journal-title":"Remote Sens"},{"key":"15608_CR218","doi-asserted-by":"crossref","unstructured":"Zhao Q, Sheng T, Wang Y, Tang Z, Chen Y, Cai L, Ling H (2018) M2det: a single-shot object detector based on multi-level feature pyramid network. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"15608_CR219","unstructured":"Zheng M, Gao P, Zhang R, Li K, Wang X, Li H, Dong H (2020) End-to-end object detection with adaptive clustering transformer. arXiv preprint arXiv:2011.09315"},{"key":"15608_CR220","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2019) Distance-iou loss: faster and better learning for bounding box regression. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"15608_CR221","unstructured":"Zhou X, Wang D, Krahenbuhl P (2019) Objects as points. arXiv$$:$$ Computer Vision and Pattern Recognition"},{"key":"15608_CR222","doi-asserted-by":"crossref","unstructured":"Zhou Z, Hu Y, Deng X, Huang D, Lin Y (2021) Fault detection of train height valve based on nanodet-resnet101. In: 2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC), IEEE, pp 709\u2013714","DOI":"10.1109\/YAC53711.2021.9486540"},{"key":"15608_CR223","doi-asserted-by":"publisher","unstructured":"Zhu P, Wen L, Du D, Bian X, Fan H, Hu Q, Ling H (2021) Detection and tracking meet drones challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence pp 1\u20131, https:\/\/doi.org\/10.1109\/TPAMI.2021.3119563","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"15608_CR224","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159"},{"key":"15608_CR225","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.rse.2011.10.028","volume":"118","author":"Z Zhu","year":"2012","unstructured":"Zhu Z, Woodcock CE (2012) Object-based cloud and cloud shadow detection in landsat imagery. Remote Sens Environ 118:83\u201394","journal-title":"Remote Sens Environ"},{"key":"15608_CR226","doi-asserted-by":"crossref","unstructured":"Zhu Z, Liang D, Zhang S, Huang X, Li B, Hu S (2016) Traffic-sign detection and classification in the wild. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2016.232"},{"key":"15608_CR227","doi-asserted-by":"crossref","unstructured":"Zhuang L, Xu Y, Ni B, Xu H (2017) Flexible network binarization with layer-wise priority. arXiv$$:$$ Computer Vision and Pattern Recognition","DOI":"10.1109\/ICIP.2018.8451576"},{"key":"15608_CR228","unstructured":"Zoph B, Le QV (2016) Neural architecture search with reinforcement learning. arXiv$$:$$ Learning"},{"key":"15608_CR229","doi-asserted-by":"crossref","unstructured":"Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00907"},{"issue":"3","key":"15608_CR230","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1109\/TIP.2017.2773199","volume":"27","author":"Z Zou","year":"2018","unstructured":"Zou Z, Shi Z (2018) Random access memories: a new paradigm for target detection in high resolution aerial remote sensing images. IEEE Trans Image Process 27(3):1100\u20131111","journal-title":"IEEE Trans Image Process"},{"key":"15608_CR231","unstructured":"Zou Z, Shi Z, Guo Y, Ye J (2019) Object detection in 20 years: a survey. arXiv$$:$$ Computer Vision and Pattern Recognition"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15608-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15608-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15608-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T16:49:52Z","timestamp":1729615792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15608-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,20]]},"references-count":231,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["15608"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15608-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,20]]},"assertion":[{"value":"18 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 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":"Author Yong Zhou, Author Lei Xia, Author Jiaqi Zhao, Author Rui Yao, Author Bing Liu declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}