[1] [1] QU Y, TIAN X F, MA L H, et al. Application of VV&A in infrared target simulator and its fidelity evaluation［J］. Infrared, 2011, 32(7):28-33(in Chinese).

[2] [2] ZHOU Y F, ZHAO J, WANG D Y, et al. Detection and evaluation of fidelity and reliability of infrared target ship［J］. Infrared, 2013, 34(7):39-44(in Chinese).

[3] [3] LI H, WANG M, GUO Zh H, et al. Fidelity research on IR capturing and tracking device based on digital image injection simulation test［J］. Modern Defense Technology, 2018, 46(2): 193-201(in Chinese).

[4] [4] MA T, GENG M. Simulation of infrared target detection system［J］. Electro-Optic Technology Application, 2017, 32(2):62-67(in Chinese).

[5] [5] GONG Y, WANG Q Q, SHAN B, et al. Quantized fidelity evaluation scheme of laser target simulator［J］.Infrared and Laser Engineering,2016,45(12):124-129(in Chinese).

[6] [6] TIAN X F, MA L H, ZHAO Sh H, et al. Fidelity evaluation scheme for IR target simulation［J］.Semiconductor,2012,33(1):135-140(in Chinese).

[7] [7] LOWE D G. Distinctive image features from scale-invariant keypoints［J］. International Journal of Computer Vision, 2004, 60(2):91-110.

[8] [8] BAY H, TUYTELAARS T, van GOOL L. Surf: Speeded up robust features［C］//The 9th European Conference on Computer Vision. Graz, Austria: Springer, 2006:404-417.

[9] [9] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters［C］//Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA:IEEE, 2010:2544-2550.

[10] [10] KRIZHEVSKY A, SUTSKEVER I, HINTON G. Image net classification with deep convolutional neural networks［C］// Twenty-fifth Conference on Neural Information Processing Systems. New York, USA: IEEE, 2012:1097-1105.

[11] [11] NEYSHABUR B, BHOJANAPALLI S, MCALLESTER D, et al. Exploring generalization in deep learning［C］//Thirty-first Conference on Neural Information Processing Systems. New York, USA: IEEE, 2017: 5949-5958.

[12] [12] SONODA S, MURATA N. Neural network with unbounded activation functions is universal approximator［J］. Applied and Computational Harmonic Analysis, 2015, 43(2):233-268.

[13] [13] MA S, BELKIN M. Diving into the shallows: a computational perspective on large-scale shallow learning［C］//Thirty-first Conference on Neural Information Processing Systems. New York, USA: IEEE, 2017: 3781-3790.

[14] [14] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):583-596.

[15] [15] REDMON J, FARHADI A. YOLO9000: Better, faster, stronger［C］//Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2017:6517-6525.

[16] [16] DONAHUE J, JIA Y, VINYALS O, et al. DeCAF: A deep convolutional activation feature for generic visual recognition［C］//Proceedings of the 31st International Conference on Machine Learning. New York, USA:IEEE, 2014:647-655.

[17] [17] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks［C］//The 13th European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014:818-833.

[18] [18] LU Z, PU H, WANG F, et al. The expressive power of neural network: A view from the width［C］//Thirty-first Conference on Neural Information Processing Systems. New York, USA: IEEE, 2017: 6231-6239.

[19] [19] YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks?［C］//Twenty-eighth Conference on Neural Information Processing Systems. New York, USA: IEEE, 2014:3320-3328.

[20] [20] HU H, ZHOU G T, DENG Z, et al. Learning structured inference neural networks with label relations［C］//Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2016:2960-2968.

[21] [21] DENG Z, VAHDAT A, HU H, et al. Structure inference machine: Recurrent neural networks for analyzing relations in group activity recognition［C］//Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2016:4772-4781.