Trocr: Transformer-based optical character recognition with pre-trained models

M Li, T Lv, J Chen, L Cui, Y Lu, D Florencio… - Proceedings of the …, 2023‏ - ojs.aaai.org
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 …

Svtr: Scene text recognition with a single visual model

Y Du, Z Chen, C Jia, X Yin, T Zheng, C Li, Y Du… - ar** field that faces numerous challenges due to
the complexity and diversity of scene text, including complex backgrounds, diverse fonts …

Hiercode: A lightweight hierarchical codebook for zero-shot chinese text recognition

Y Zhang, Y Zhu, D Peng, P Zhang, Z Yang, Z Yang… - Pattern Recognition, 2025‏ - Elsevier
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 …

A benchmark for Chinese-English scene text image super-resolution

J Ma, Z Liang, W **ang, X Yang… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Abstract Scene Text Image Super-resolution (STISR) aims to recover high-resolution (HR)
scene text images with visually pleasant and readable text content from the given low …