Han Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Han Xu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Runmin Wang
Hunan Normal University, Changsha, China
2 shared publications - Shengyou Qian
School of Physical and Electronic Sciences, Hunan Normal University, Changsha, China
2 shared publications - Xingdong Song
School of Information Science and Engineering, Hunan Normal University, Changsha, China
2 shared publications - Changxin Gao
Huazhong University of Science and Technology
1 shared publication - Congzhen Yu
Hunan Normal University, School of Information Science and Engineering, Changsha, China
1 shared publication - Nong Sang
Huazhong University of Science and Technology
1 shared publication
Latest Publications
- 24 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 7894-7908
MSINet: A Mask Structure Inference Network for Scene Text Image Super-Resolution
Understanding the structure of characters is crucial for recovering clear and readable high-resolution scene text images in Scene Text Image Super-Resolution (STISR). Recently, many existing STISR methods inject the character structure information implicit in the recognition priors into the super-resolution network to guide the super-resolution process, thereby facilitating the generation of more legible text images. However, the recognition priors obtained from low resolution are inaccurate, which means that directly embedding these priors into the network easily misleads the super-resolution process. To address this problem, we draw inspiration from Masked Image Modeling (MIM) and propose the Mask Structure Inference Network (MSINet), which can generate scene text images with accurate character structures without directly embedding recognition priors. To make STISR compatible with MIM, we also propose a Mask-and-Inference Paradigm (MIP), which consists of a mask image pre-training stage for character structure learning and a fine-tuning stage for character structure inference. In addition, a novel mask strategy named Text Confidence Mask (TCM) is proposed to avoid recovery errors by masking legible character regions. With MIP and TCM, MSINet impressively improves the clarity and readability of the degraded scene text images. Specifically, MSINet-B outperforms recent state-of-the-art methods by about +3.7% on the TextZoom and average +3.6% on six manually degraded scene text recognition datasets in recognition accuracy. The code will be released at https://github.com/Yuanssr/MSINet.
- 24 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 7894-7908
MSINet: A Mask Structure Inference Network for Scene Text Image Super-Resolution
Understanding the structure of characters is crucial for recovering clear and readable high-resolution scene text images in Scene Text Image Super-Resolution (STISR). Recently, many existing STISR methods inject the character structure information implicit in the recognition priors into the super-resolution network to guide the super-resolution process, thereby facilitating the generation of more legible text images. However, the recognition priors obtained from low resolution are inaccurate, which means that directly embedding these priors into the network easily misleads the super-resolution process. To address this problem, we draw inspiration from Masked Image Modeling (MIM) and propose the Mask Structure Inference Network (MSINet), which can generate scene text images with accurate character structures without directly embedding recognition priors. To make STISR compatible with MIM, we also propose a Mask-and-Inference Paradigm (MIP), which consists of a mask image pre-training stage for character structure learning and a fine-tuning stage for character structure inference. In addition, a novel mask strategy named Text Confidence Mask (TCM) is proposed to avoid recovery errors by masking legible character regions. With MIP and TCM, MSINet impressively improves the clarity and readability of the degraded scene text images. Specifically, MSINet-B outperforms recent state-of-the-art methods by about +3.7% on the TextZoom and average +3.6% on six manually degraded scene text recognition datasets in recognition accuracy. The code will be released at https://github.com/Yuanssr/MSINet.
- 27 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 311
Dual-space intervention for mitigating bias in robust visual question answering
- 27 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 311
Dual-space intervention for mitigating bias in robust visual question answering