[1] [1] Yao A, Shao J, Ma N, et al. Capturing auaware facial features their latent relations f emotion recognition in the wild[C]Proceedings of the ACM International Conference on Multimodal Interaction, 2015: 451458.

[2] D Kang, H Shim, K Yoon. A method for extracting emotion using colors comprise the painting image. Multimedia Tools and Applications, 77, 4985-5002(2018).

[3] K Song, T Yao, Q Ling. Boosting image sentiment analysis with visual attention. Neurocomputing, 312, 218-228(2018).

[4] X He, W Zhang. Emotion recognition by assisted learning with convolutional neural networks. Neurocomputing, 291, 187-194(2018).

[5] D Castelvecchi. Can we open the black box of AI?. Nature, 538, 20-23(2016).

[6] [6] Voosen P. How AI detectives are cracking open the black box of deep learning[EBOL]. [20190912]. https:doi.g10.1126science.aan7059.

[7] R Fu, B Li, Y Gao. Visualizing and analyzing convolution neural networks with gradient information. Neurocomputing, 293, 12-17(2018).

[8] [8] Olah C, Mdvintsev A, Schubert L. Feature visualization[C] IEEE Transactions on Visualization Computer Graphics, 2020, 26(1): 2034594.

[9] C Olah, A Satyanarayan, I Johnson. The building blocks of interpretability. Distill, 00010(2018).

[10] [10] Zhou B, Khosla A, Lapedriza A, et al. Learning deep features f discriminative localization[C]Proceedings of the IEEE Conference on Computer Vision Pattern Recognition, 2016: 29212929.

[11] [11] Selvaraju R R, Cogswell M, Das A, et al. GradCAM: Visual explanations from deep wks via gradientbased localization[C]Proceedings of the International Conference on Computer Vision, 2017: 618626.

[12] [12] Zeiler M D, Fergus R. Visualizing understing convolutional wks[C]Proceedings of the European Conference on Computer Vision, 2014: 818833.

[13] [13] Fong R, Vedaldi A. Interpretable explanations of black boxes by meaningful perturbation[C]Proceedings of the International Conference on Computer Vision, 2017: 34493457.

[14] Yuzhi Li, Jiachuan Sheng, Bin Hua. Improved embedded learning for classification of Chinese paintings. Journal of Computer-Aided Design & Computer Graphics, 30, 893-900(2018).

[15] Jiachuan Sheng, Yuzhi Li. Learning artistic objects for improved classification of Chinese paintings. Journal of Image and Graphics, 23, 1193-1206(2018).

[16] Pengfei Liu, Huaici Zhao, Feidao Cao. Blind deblurring of noisy and blurry images of multi-scale convolutional neural network. Infrared and Laser Engineering, 48, 0426001(2019).

[17] Shengnan Fang, Xiaojing Gu, Xingsheng Gu. Infrared target tracking with correlation filter based on adaptive fusion of responses. Infrared and Laser Engineering, 48, 0626003(2019).

[18] Shanjiang Hu, Yan He, Bangyi Tao. Classification of sea and land waveforms with deep learning for airborne laser bathymetry. Infrared and Laser Engineering, 48, 1113004(2019).

[19] J Sheng, Y Li. Classification of traditional Chinese paintings using a modified embedding algorithm. Journal of Electronic Imaging, 28, 023013(2019).

[20] [20] Sheng J, Song C, Wang J, et al. Convolutional neural wk style transfer towards chinese paintings[C]IEEE Access, 2019, 7: 163719163728.

[21] [21] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]Proceedings of the IEEE Conference on Computer Vision Pattern Recognition, 2015: 19.

[22] [22] Simonyan K, Zisserman A. Very deep convolutional wks f largescale image recognition[C]Proceedings of the International Conference on Learning Representations, 2015: 114.

[23] [23] Erhan D, Bengio Y, Courville A, et al. Visualizing higherlayer features of a deep wk[D]. Canada: University of Montreal, 2009.

[24] [24] Lin M, Chen Q, Yan S. wk in wk[C]Proceedings of the International Conference on Learning Representations, 2014: 110.

[25] [25] You Q, Luo J, Jin H, et al. Robust image sentiment analysis using progressively trained domain transferred deep wks[C]Proceedings of the AAAI Conference on Artificial Intelligence, 2015: 381388.