The history of text can be traced back over thousands of years. Rich and precise semantic
information carried by text is important in a wide range of vision-based application …

Context-aware STR methods typically use internal autoregressive (AR) language models
(LM). Inherent limitations of AR models motivated two-stage methods which employ an …

Text in natural scene images plays a vital role in scene understanding. It contains a rich and
abundant amount of valuable semantic information useful in many applications such as …

Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively
model linguistic rules in end-to-end deep networks remains a research challenge. In this …

Current text recognition systems, including those for handwritten scripts and scene text, have
relied heavily on image synthesis and augmentation, since it is difficult to realize real-world …

In the 1940s, Claude Shannon developed the information theory focusing on quantifying the
maximum data rate that can be supported by a communication channel. Guided by this …

In this paper, we abandon the dominant complex language model and rethink the linguistic
learning process in the scene text recognition. Different from previous methods considering …

Scene text recognition (STR) enables computers to read text in natural scenes such as
object labels, road signs and instructions. STR helps machines perform informed decisions …

Typical text recognition methods rely on an encoder-decoder structure, in which the encoder
extracts features from an image, and the decoder produces recognized text from these …

Image super-resolution, which is often regarded as a preprocessing procedure of scene text
recognition, aims to recover the realistic features from a low-resolution text image. It has …