Authors: Hong Wang (CAS), Weiyuan Shao(FDU), Haonan Qiu (ECNU), Jianqi Ma (FDU), Zhiqiang Shen (CMU)

Description: The recognition network is a CRNN-like structure. We modified the original CRNN by using a list of cropped images rather than a single one as inputs. We also pre-train network parameters on ReCTS19
task1 dataset to accelerate convergence.