1 code implementation • ACM International Conference on Multimedia 2021 • Zhao Cairong, Feng Shuyang, Zhao Brian Nlong, Ding Zhijun, Wu Jun, Shen Fumin, Shen Heng Tao
In this paper, we propose a Parallel Contextual Attention Network (PCAN), which can effectively learn sequence-dependent features and focus more on high-frequency information of the reconstruction in text images.