@inproceedings{96c66d13f50f44d2813cede005d52347,
title = "Scene Text Recognition with Temporal Convolutional Encoder",
abstract = "Texts from scene images typically consist of several characters and exhibit a characteristic sequence structure. Existing methods capture the structure with the sequence-to-sequence models by an encoder to have the visual representations and then a decoder to translate the features into the label sequence. In this paper, we study text recognition framework by considering the long-term temporal dependencies in the encoder stage. We demonstrate that the proposed Temporal Convolutional Encoder with increased sequential extents improves the accuracy of text recognition. We also study the impact of different attention modules in convolutional blocks for learning accurate text representations. We conduct comparisons on seven datasets and the experiments demonstrate the effectiveness of our proposed approach.",
keywords = "Scene text recognition, sequence model, temporal convolutions",
author = "Xiangcheng Du and Tianlong Ma and Yingbin Zheng and Hao Ye and Xingjiao Wu and Liang He",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 ; Conference date: 04-05-2020 Through 08-05-2020",
year = "2020",
month = may,
doi = "10.1109/ICASSP40776.2020.9054269",
language = "英语",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2383--2387",
booktitle = "2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings",
address = "美国",
}