@article{Hu_Cai_Hou_Yi_Lin_2020, title={GTC: Guided Training of CTC towards Efficient and Accurate Scene Text Recognition}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/6735}, DOI={10.1609/aaai.v34i07.6735}, abstractNote={<p>Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower accuracy. To design an efficient and effective model, we propose the guided training of CTC (GTC), where CTC model learns a better alignment and feature representations from a more powerful attentional guidance. With the benefit of guided training, CTC model achieves robust and accurate prediction for both regular and irregular scene text while maintaining a fast inference speed. Moreover, to further leverage the potential of CTC decoder, a graph convolutional network (GCN) is proposed to learn the local correlations of extracted features. Extensive experiments on standard benchmarks demonstrate that our end-to-end model achieves a new state-of-the-art for regular and irregular scene text recognition and needs 6 times shorter inference time than attention-based methods.</p>}, number={07}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Hu, Wenyang and Cai, Xiaocong and Hou, Jun and Yi, Shuai and Lin, Zhiping}, year={2020}, month={Apr.}, pages={11005-11012} }