In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify
vision-language tasks such as image/video captioning and question answering. While …

Text recognition is a long-standing research problem for document digitalization. Existing
approaches are usually built based on CNN for image understanding and RNN for char …

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 …

As the deep learning revolution marches on, self-supervised learning has garnered
increasing attention in recent years thanks to its remarkable representation learning ability …

Scene text images contain not only style information (font background) but also content
information (character texture). Different scene text tasks need different information but …

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 …

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 …

Reading text in real-world scenarios often requires understanding the context surrounding it,
especially when dealing with poor-quality text. However, current scene text recognizers are …

Text recognition, especially for complex scripts like Chinese, faces unique challenges due to
its intricate character structures and vast vocabulary. Traditional one-hot encoding methods …

Proper interaction between visual and semantic features is crucial to obtain a powerful
feature representation for scene text recognition (STR). The existing interaction methods …