no code implementations • 20 Mar 2024 • Yuyi Zhang, Yuanzhi Zhu, Dezhi Peng, Peirong Zhang, Zhenhua Yang, Zhibo Yang, Cong Yao, Lianwen Jin
Text recognition, especially for complex scripts like Chinese, faces unique challenges due to its intricate character structures and vast vocabulary.
no code implementations • CVPR 2023 • Yuanzhi Zhu, Zhaohai Li, Tianwei Wang, Mengchao He, Cong Yao
Current text recognition systems, including those for handwritten scripts and scene text, have relied heavily on image synthesis and augmentation, since it is difficult to realize real-world complexity and diversity through collecting and annotating enough real text images.
2 code implementations • 15 May 2023 • Yuanzhi Zhu, Kai Zhang, Jingyun Liang, JieZhang Cao, Bihan Wen, Radu Timofte, Luc van Gool
Although diffusion models have shown impressive performance for high-quality image synthesis, their potential to serve as a generative denoiser prior to the plug-and-play IR methods remains to be further explored.
3 code implementations • ICCV 2023 • Zixiang Zhao, Haowen Bai, Yuanzhi Zhu, Jiangshe Zhang, Shuang Xu, Yulun Zhang, Kai Zhang, Deyu Meng, Radu Timofte, Luc van Gool
To leverage strong generative priors and address challenges such as unstable training and lack of interpretability for GAN-based generative methods, we propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM).
no code implementations • 23 Feb 2022 • Canjie Luo, Yuanzhi Zhu, Lianwen Jin, Zhe Li, Dezhi Peng
Specifically, we propose a style bank to parameterize the specific handwriting styles as latent vectors, which are input to a generator as style priors to achieve the corresponding handwritten styles.
1 code implementation • CVPR 2021 • Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Dezhi Peng, Zhe Li, Mengchao He, Yongpan Wang, Canjie Luo
Specifically, we integrate IFA into the two most prevailing text recognition streams (attention-based and CTC-based) and propose attention-guided dense prediction (ADP) and Extended CTC (ExCTC).
Optical Character Recognition Optical Character Recognition (OCR) +1
1 code implementation • 7 May 2020 • Xiaoxue Chen, Lianwen Jin, Yuanzhi Zhu, Canjie Luo, Tianwei Wang
This paper aims to (1) summarize the fundamental problems and the state-of-the-art associated with scene text recognition; (2) introduce new insights and ideas; (3) provide a comprehensive review of publicly available resources; (4) point out directions for future work.
3 code implementations • CVPR 2020 • Canjie Luo, Yuanzhi Zhu, Lianwen Jin, Yongpan Wang
An agent network learns from the output of the recognition network and controls the fiducial points to generate more proper training samples for the recognition network.
4 code implementations • 21 Dec 2019 • Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Canjie Luo, Xiaoxue Chen, Yaqiang Wu, Qianying Wang, Mingxiang Cai
To remedy this issue, we propose a decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results.
Ranked #4 on Scene Text Recognition on ICDAR 2003
no code implementations • 26 Aug 2019 • Xiaoxue Chen, Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Canjie Luo
Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications.
2 code implementations • CVPR 2019 • Zecheng Xie, Yaoxiong Huang, Yuanzhi Zhu, Lianwen Jin, Yuliang Liu, Lele Xie
In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective.