This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective.
We begin by revisiting the six commonly used benchmarks in STR and observe a trend of …

Many new proposals for scene text recognition (STR) models have been introduced in
recent years. While each claim to have pushed the boundary of the technology, a holistic …

Dominant scene text recognition models commonly contain two building blocks, a visual
model for feature extraction and a sequence model for text transcription. This hybrid …

Scene text recognition (STR) task has a common practice: All state-of-the-art STR models
are trained on large synthetic data. In contrast to this practice, training STR models only on …

Reading text in the wild is a very challenging task due to the diversity of text instances and
the complexity of natural scenes. Recently, the community has paid increasing attention to …

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 …

We address the problem of image feature learning for scene text recognition. The image
features in the state-of-the-art methods are learned from large-scale synthetic image …

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 …

The pursuit of high performance on public benchmarks has been the driving force for
research in scene text recognition, and notable progresses have been achieved. However, a …

Abstract Existing Scene Text Recognition (STR) methods typically use a language model to
optimize the joint probability of the 1D character sequence predicted by a visual recognition …