Fan Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fan Yang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Jiahao Shen
1 shared publicationKejun Ren
1 shared publication- Mingcai Chen
School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, Jangsu, China and State Key Lab. of Novel Software Technology, Nanjing University, Nanjing, Jangsu, China
1 shared publication - Tong Tang
Chongqing University of Posts and Telecommunications
1 shared publication - Weisheng Li
Chongqing University of Posts and Telecommunications
1 shared publication Xinyu Lin
School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China
1 shared publication
Latest Publications
- 26 February 2026
- Published by Elsevier in Information Fusion
- Vol. 133
Uncertainty and diversity based selection for active learning in vision-language models
- 26 February 2026
- Published by Elsevier in Information Fusion
- Vol. 133
Uncertainty and diversity based selection for active learning in vision-language models
- 21 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1366-1370
Dual-Branch Network for No-Reference Super-Resolution Image Quality Assessment
No-reference super-resolution image quality assessment (SR-IQA) has become an critical technique for optimizing SR algorithms, the key challenge is how to comprehensively learn visual related features of SR image. Existing methods ignore the context information and feature correlation. To tackle this problem, this paper proposes a dual-branch network for noreference super-resolution image quality assessment (DBSRNet). First, dual-branch feature extraction module is designed, where residual network and receptive field block net are combined to learn multi-scale local features, stacked vision transformer blocks are utilized to learn global features. Then, correlations between dual-branch features are learned and fused based on selfattention mechanism structure, final predicted score is obtained by adaptive feature pooling strategy. Finally, experimental results show that DBSRNet significantly outperforms state-of-the-art methods in terms of prediction accuracy on all SR-IQA datasets. The source code will be released in https://github.com/Yangfan123-cell/DBSRNet.
- 21 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1366-1370
Dual-Branch Network for No-Reference Super-Resolution Image Quality Assessment
No-reference super-resolution image quality assessment (SR-IQA) has become an critical technique for optimizing SR algorithms, the key challenge is how to comprehensively learn visual related features of SR image. Existing methods ignore the context information and feature correlation. To tackle this problem, this paper proposes a dual-branch network for noreference super-resolution image quality assessment (DBSRNet). First, dual-branch feature extraction module is designed, where residual network and receptive field block net are combined to learn multi-scale local features, stacked vision transformer blocks are utilized to learn global features. Then, correlations between dual-branch features are learned and fused based on selfattention mechanism structure, final predicted score is obtained by adaptive feature pooling strategy. Finally, experimental results show that DBSRNet significantly outperforms state-of-the-art methods in terms of prediction accuracy on all SR-IQA datasets. The source code will be released in https://github.com/Yangfan123-cell/DBSRNet.