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 image contains two levels of contents: visual texture and semantic information.
Although the previous scene text recognition methods have made great progress over the …

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 …

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 …

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 …

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 …

Attention-based scene text recognizers have gained huge success, which leverages a more
compact intermediate representation to learn 1d-or 2d-attention by a RNN-based encoder …

In this paper, we explore the potential of the Contrastive Language-Image Pretraining (CLIP)
model in scene text recognition (STR), and establish a novel Symmetrical Linguistic Feature …

Linguistic knowledge has brought great benefits to scene text recognition by providing
semantics to refine character sequences. However, since linguistic knowledge has been …

Nowadays, scene text recognition has attracted more and more attention due to its various
applications. Most state-of-the-art methods adopt an encoder-decoder framework with …