[3] [3] Gaurav Bhatt. Representation learning using step-based deep multi-modal autoencoders［J］. Pattern Recognition,2019,95:12-23.

[4] [4] Xiao X, Wang L, Ding K, et al. Dense semantic embedding network for image captioning［J］. Pattern Recognition,2019,90:285-296.

[7] [7] Gao X, Sun J, Liu Z, et al. Highly efficient preparation of free all-trans-astaxanthin from Haematococcus pluvialis extract by a rapid biocatalytic method based on crude extracellular enzyme extract［J］. International Journal of Food Ence & Technology,2019,54(2):376-386.

[9] [9] Hu Q, Zhai L. RGB-D image multi-target detection method based on 3d dsf R-CNN［J］. International Journal of Pattern Recognition and Artificial Intelligence,2019,33(8):1-15.

[11] [11] Wang D, Mao K . Learning semantic text features for web text aided image classification［J］. IEEE Transactions on Multimedia,2019,21(12): 2985-2996.

[12] [12] Ma K, Chen X, Zhu K, et al. A method to extract essential information from meteorological facsimile charts［J］. International Journal of Pattern Recognition and Artificial Intelligence,2019,33(1):1-16.

[14] [14] Gan Z, Gan C, He X, et al. Semantic compositional networks for visual captioning［J］. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2017,127(10):1109.

[15] [15] Kai Niu. Re-ranking image-text matching by adaptive metric fusion［J］. Pattern Recognition,2020,104(107351):1-13.

[17] [17] Li Y, Yang M, Zhang Z. A survey of multi-view representation learning［J］. IEEE Transactions on Knowledge and Data Engineering,2019,31(10):1863-1883.

[20] [20] Lin B, Fang B, Yang W, et al. Human action recognition based on spatio-temporal three-dimensional scattering transform descriptor and an improved VLAD feature encoding algorithm［J］. Neurocomputing,2019,348(07):145-157.