Preprint

1. Zhang, Weixia; Li, Dingquan; Zhai, Guangtao; Yang, Xiaokang; & Ma, Kede (2024). Comparison of No-Reference Image Quality Models via MAP Estimation in Diffusion Latents. arXiv preprint arXiv:2403.06406. [PDF]

2. Zhang, Weixia; Zhu, Chengguang; Gao, Jingnan; Yan, Yichao; Zhai, Guangtao; & Yang, Xiaokang (2024). A Comparative Study of Perceptual Quality Metrics for Audio-driven Talking Head Videos. arXiv preprint arXiv:2403.06421. [PDF]

3. Wu, Haoning; Zhang, Zicheng; Zhang, Weixia; Chen, Chaofeng; Liao, Liang; Li, Chunyi; Gao, Yixuan Gao; Wang, Annan; Zhang, Erli; Sun, Wenxiu; Yan, Qiong; Min, Xiongkuo; Zhai, Guangtao; & Lin, Weisi (2023). Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels. arXiv preprint arXiv:2312.17090. [PDF]

Journal

First authored papers

1. Zhang, Weixia; Ma, Kede; Zhai, Guangtao & Yang, Xiaokang (2024). Task-Specific Normalization for Continual Learning of Blind Image Quality Models. IEEE Transactions on Image Processing (TIP), 33, 1898-1910. [PDF] [Github] 

2. Zhang, Weixia; Li, Dingquan; Ma, Chao; Zhai, Guangtao; Yang, Xiaokang & Ma, Kede (2023). Continual Learning for Blind Image Quality Assessment. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(3), 2864-2878. [PDF] [Github] 

3. Zhang, Weixia; Ma, Kede; Zhai, Guangtao & Yang, Xiaokang (2021). Uncertainty-aware blind image quality assessment in the laboratory and wild. IEEE Transactions on Image Processing (TIP), vol. 30, pp. 3474-3486, Mar. 2021.  [PDF] [Github] 

4. Zhang, Weixia; Ma, Chao; Wu, Qi; & Yang, Xiaokang (2020). Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). [PDF] 

5. Zhang, Weixia; Ma, Kede; Yan, Jia; Deng, Dexiang & Wang, Zhou (2020). Blind image quality assessment using a deep bilinear convolutional neural network. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 30(1), 36-47.[PDF][Github--PyTorch] [Github--Matlab] 

6.  Zhang, Weixia; Yan, Jia; Hu, Shiyong; Ma, Yang & Deng, Dexiang (2018). Predicting perceptual quality of images in realistic scenario using deep filter banks. Journal of Electronic Imaging (JEI), 27(2), 023037.[PDF]

7. 张维夏, 邓德祥 & 颜佳. (2018). 基于多通道特征聚合的盲图像质量评价. 华中科技大学学报 (自然科学版), 7.

8. Zhang, Weixia; Yan, Jia; Shi, Wenxuan; Feng, Tianpeng & Deng, Dexiang (2017). Refining deep convolutional features for improving fine-grained image recognition. EURASIP Journal on Image and Video Processing, 2017(1), 1-10.[PDF]

Co-authored papers

9. Yan, Yichao; Cheng, Yuhao; Chen, Zhuo; Peng, Yicong; Wu, Sijing; Zhang, Weitian; Li, Junjie; Li, Yixuan; Gao, Jinnan; Zhang, Weixia; Zhai, Guangtao & Yang, Xiaokang (2023). 基于神经网络的生成式数字人研究综述：表示、渲染与学习. 中国科学：信息科学 [PDF]

10. Li, Bowen; Zhang, Weixia; Tian, Meng; Zhai, Guangtao & Wang, Xianpei (2022). Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). [PDF] [Github] 

11. 李博文，田猛，张维夏 & 王先培. (2021). 基于多层级信息稀疏表征的盲图像质量评价. 华中科技大学学报 (自然科学版).

12. Li, Bowen; Tian, Meng; Zhang, Weixia; Yao, Hongtai, & Wang, Xianpei (2021). Learning to predict the quality of distorted-then-compressed images via a deep neural network. Journal of Visual Communication and Image Representation (JVCIR), 76, 103004.[PDF]

13. Li, Bowen; Wang, Xianpei; Zhang, Weixia; Tian, Meng; & Yao, Hongtai. (2020). Dual Head Network for No-Reference Quality Assessment Towards Realistic Night-Time Images. IEEE Access, 8, 158585-158599.[PDF]

14. Hu, Shiyong; Yan, Jia; Zhang, Weixia & Deng, Dexiang. (2019). No-reference quality assessment for contrast-altered images using an end-to-end deep framework. Journal of Electronic Imaging (JEI), 28(1), 013041.[PDF]

15. Ma, Yang; Zhang, Weixia; Yan, Jia; Fan, Cien & Shi, Wenxuan (2018). Blind image quality assessment in multiple bandpass and redundancy domains. Digital Signal Processing (DSP), 80, 37-47.[PDF]

16. Feng, Tianpeng; Deng, Dexiang; Yan, Jia; Zhang, Weixia; Shi, Wenxuan & Zou, Lian (2016). Sparse representation of salient regions for no-reference image quality assessment. International Journal of Advanced Robotic Systems, 13(5), 1729881416669486.[PDF]

Conference

First authored papers

1. Zhang, Weixia; Zhai, Guangtao; Ying Wei; Yang, Xiaokang & Ma, Kede (2023). Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [PDF][Github] 

2. Zhang, Weixia; Li, Dingquan; Min, Xiongkuo; Zhai, Guangtao; Guo, Guodong; Yang, Xiaokang & Ma, Kede (2022). Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop. Conference on Neural Information Processing Systems (NeurIPS), spotlight (5%). [PDF][Github] 

3. Zhang, Weixia; Ma, Kede; Zhai, Guangtao & Yang, Xiaokang (2020). Learning to blindly assess image quality in the laboratory and wild. In 2020 IEEE International Conference on Image Processing (ICIP) (pp. 111-115). [PDF] [Github] 

4. Zhang, Weixia; Zhai, Guangtao; Yang, Xiaokang & Yan, Jia (2019). Hierarchical features fusion for image aesthetics assessment. In 2019 IEEE International Conference on Image Processing (ICIP) (pp. 3771-3775). [PDF] [Github] 

Co-authored papers

5. Yi, Xunpeng; Wang, Yuxuan; Zhao, Yizhen; Yan, Jia & Zhang, Weixia (2023). Llieformer: A Low-Light Image Enhancement Transformer Network with a Degraded Restoration Model. IEEE International Conference on Image Processing (ICIP) (pp. 1195-1199). [PDF]

6. Li, Bowen; Zhang, Weixia (corresponding author); Tian, Meng; Jiang, Jiu; Zhai, Guangtao & Wang, Xianpei (2022). Learning a blind quality evaluator for UGC videos in perceptually relevant domains. IEEE Conference on Multimedia and Expo (ICME). [PDF] [Github] 

7. Yan, Jia; Zhang, Weixia & Feng, Tianpeng (2016). Blind image quality assessment based on natural redundancy statistics. In Asian Conference on Computer Vision (ACCV) (pp. 3-18). Springer, Cham.