Pre-trained vision-language models~(VLMs) are the de-facto foundation models for various downstream tasks. However, scene text recognition methods still prefer backbones pre …
T Wang, Y Zhu, L Jin, D Peng, Z Li… - Proceedings of the …, 2021 - openaccess.thecvf.com
Text recognition is a popular research subject with many associated challenges. Despite the considerable progress made in recent years, the text recognition task itself is still …
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 …
Q Jiang, J Wang, D Peng, C Liu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
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 …
Y Zhang, Z Fu, F Huang, Y Liu - Pattern Recognition Letters, 2021 - Elsevier
Abstract Scene Text Recognition (STR) task needs to consume large-amount data to develop a powerful recognizer, including visual data like images and linguistic data like …
S Fang, H Xie, Y Wang, Z Mao… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …
Over the past few years, several new methods for scene text recognition have been proposed. Most of these methods propose novel building blocks for neural networks. These …
Abstract Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still …