[1] Yilmaz A, Javed O, Shah M. Object tracking[J.] ACM Comput Surv, 2006, 38(4): 13.
[2] Bao C, Wu Y, Ling H, et al. Real time robust L1 tracker using accelerated proximal gradient approach[J]. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, 2012, 157(10): 1830-1837.
[3] Bertinetto L, Valmadre J, Golodetz S, et al. Staple: Complementary Learners for Real-Time Tracking[M]. Oxford: University of Oxford, 2015: 1401-1409.
[4] Luo J, Konofagou E. A fast normalized cross-correlation calculation method for motion estimation[J]. IEEE Trans Ultrason Ferroelectr Freq Control, 2010, 57(6): 1347-1357.
[5] Chang C, Ansari R. Kernel particle filter for visual tracking[J]. IEEE Signal Process Lett, 2005,12(3): 242-245.
[6] Amiaz T, Lubetzky E, Kiryati N. Coarse to over-fine optical flow estimation[J]. Pattern Recognit, 2007, 40(9): 2496-2503.
[7] Comaniciu D, Meer P, Member S. Mean Shift: a robust approach toward feature space analysis[J]. IEEE Transaction on Pattern Analasys and Machine Intelligence, 2002, 24(5): 603-619.
[8] Shi Zelin, Wang Junqing, Huang Shabai. Tracking of deformable objects in complex scene[J]. Opto-Electronic Engineering, 2005, 32(1): 2-6.
[9] Zhang T, Bibi A, Ghanem B. In defense of sparse tracking: circulant sparse tracker[C]//CVPR, 2016, 3: 1-8.
[10] Tao R, Gavves E, Smeulders A W M. Siamese Instance Search for Tracking[C]//CVPR, 2016: 1420-1429.
[11] Kalal Z, Mikolajczyk K, Matas J. Tracking-Learning-Detection[J]. IEEE Transaction on Pattern Analasys and Machine Intelligence, 2010, 6(1): 1-14.
[12] Hare S, Saffari A, Torr P H S. Struck_ Structured output tracking with kernels[C]//2011 IEEE International Conference on Computer Vision, 2011: 263-270.
[13] Henriques J F, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters[J]. EEE Trans Pattern Anal Mach Intell, 2015, 37(3): 583-596.
[14] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networksr[J]//Science,2006, 313(5786): 504-507.
[15] Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[16] Held D, Thrun S, Savarese S. Learning to track at 100 FPS with deep regression networks[C]//ECCV, 2016, 9905: 749-765.
[17] Wang N, Yeung D Y. Learning a deep compact image representation for visual tracking[C]//Adv Neural Inf Process Syst, 2013: 1-9.
[18] VOT Challenge. VOT2013 Benchmark[EB/OL]. [2017-04-20]: http://www.votchallenge.net/vot2013/.
[19] Danelljan M, Robinson A, Khan F S, et al. Felsberg, Beyond correlation filters: Learning continuous convolution operators for visual tracking[C]//ECCV 2016, 2016, 9909: 472-488.
[20] Qi Y, Zhang S, Qin L, et al. Hedged Deep Tracking[C]//CVPR, 2016: 4303-4311.
[21] Wang L, Ouyang W, Wang X, et al. Stct: Sequentially training convolutional networks for visual tracking[C]//IEEE Conf Comput Vis Pattern Recognit, 2016: 1373-1381.
[22] Nam H, Han B. Learning multi-domain convolutional neural networks for visual tracking[J]. Computer Science, 2015: 4293-4302.
[23] Nam H, Baek M, Han B. Modeling and propagating CNNs in a tree structure for visual tracking[C]//European Conference on Computer Vision, 2016: 1-10.
[24] Cui Z, Xiao S, Feng J, et al. Recurrently target-attending tracking[J]. IEEE Conf Comput Vis Pattern Recognit, 2016: 1449-1458.
[25] Ning Guanghan, Zhang Zhi, Huang Chen, et al. Spatially supervised recurrent convolutional neural networks for visual object tracking[C]//CVPR 2016, 2016.