method: NPU-ASGO2019-04-29

Authors: Ye Gao,Zhen Liu,Lu Yang,Linjiang Zhang,Hui Li,Peng Wang,Jiadai Sun,Yixuan Luo,Haobo Chen,Xiaofeng Yang

Description: In this work, we propose an easy-to-implement strong baseline for irregular scene text recognition using off-the-shelf neural network components and only word-level an notations. It is composed of a 31-layer ResNet, an LSTM based encoder-decoder framework and a 2-dimensional attention module.Despite its simplicity, the proposed method is robust and achieves state-of-the-art performance on both regular and irregular scene text recognition benchmarks.