[1] Tian Jing. Study on the Terracotta Warriors of Qin Mausoleum from the Perspective of World Heritage[J]. Emperor Qin Shihuang Mausoleum Museum, 1-17(2018).
[2] Li Gang, Tian Y Q, Xiao J Y et al. Review of archaeological discoveries and research of the Qin-Han periods in Shaanxi(2008-2017)[J]. Archaeology and Cultural Relics, 229, 66-110(2018).
[3] Lan D S. Research on adhesive materials for restoration of painted pottery figurines excavated from Pit No.1 of the Qin Terracotta Warriors and Horses[J]. Sciences of Conservation and Archaeology, 31, 49-59(2019).
[4] Tang T. Research on the application of three-dimensional technology in material cultural heritage “restoration”[D](2018).
[5] Zhao S Z, Hou M L, Li A Q et al. A classification technology of terra-cotta warriors’ fragments with multiple features[J]. Geomatics World, 26, 14-21(2019).
[6] Li W M. Design and implementation of virtual restoration system for damaged cultural relics[D](2020).
[7] Wei Y. Research on image classification and retrieval technology of terra-cotta warriors fragments based on multi-feature[D](2018).
[8] Kang X Y. Research on method of computer aided 3D models of terra-cotta warriors fragments classification[D](2015).
[9] Wang N. Research on multi-kernel semi-supervised classification of manifold regularization based on sparse graphs[D](2018).
[10] He G. Research on semi-supervised collaborative classification of terra-cotta warriors fragments based on graph[D](2019).
[11] Wang Y Y. Research on the classification algorithm of terracotta warrior fragments based on the optimization model of convolutional neural network[D](2019).
[12] Wu Z W. Application research of convolution neural network in image classification[D](2015).
[17] Szegedy C, Liu W, Jia Y Q et al. Going deeper with convolutions[C](2015).
[21] Ma Y J, Liu P P. Convolutional neural network based on DenseNet evolution for image classification algorithm[J]. Laser & Optoelectronics Progress, 57, 241001(2020).
[22] Zhang X D, Wang T J, Yang Y. Classification of small-sized sample hyperspectral images based on multi-scale residual network[J]. Laser & Optoelectronics Progress, 57, 162801(2020).
[23] Feng F, Wang S T, Zhang J et al. Hyperspectral images classification based on multi-feature fusion and hybrid convolutional neural networks[J]. Laser & Optoelectronics Progress, 58, 0810010(2021).
[27] Wang L Q, Chu X L, Qin Z C et al. Hierarchical attention for image captioning with multi-level image representations[J]. Journal of China Academy of Electronics and Information Technology, 15, 63-68(2020).
[28] Liu J M, Xie W J, Huang H et al. Spatial and channel attention mechanism method for object tracking[J]. Journal of Electronics & Information Technology, 43, 2569-2576(2021).
[29] Srivastava N, Hinton G E, Krizhevsky A et al. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 15, 1929-1958(2014).