Personal profile
Personal profile
Xianxu Hou is an Assistant Professor at the School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang). He previously worked at Shenzhen University for five years. He received his Ph.D. from the University of Nottingham (2018), as well as Masters and Bachelors degrees from China University of Mining and Technology (Beijing) in 2014 and 2011, respectively. As a deep learning researcher, he focuses on generative modeling, particularly in the areas of generative adversarial networks and diffusion models. He applies these techniques to face image generation and manipulation, with the aim of creating more realistic and controllable images.
I'm seeking highly motivated PhD students who are eager to actively engage in research on generative AI.
You can find more about my research on my website and Google Scholar.
Research interests
Generative Adversarial Network (GAN)
Diffusion Model
Face Generation and Manipulation
Image Enhancement
Medical Image Analysis
Experience
Assistant Professor, Xian Jiaotong-Liverpool University - 2023 to present
Associate Researcher, Shenzhen University, 2020-2023
Postdoctoral researcher, Shenzhen University, 2018-2020
Education/Academic qualification
PhD, University of Nottingham, 2018
MSc, China University of Mining and Technology, Beijing, 2014
BSc, China University of Mining and Technology, Beijing, 2011
Research areas
- Deep Learning
- Generative Model
- Diffusion Model
- MLLM
Person Types
- Staff
Fingerprint
- 1 Similar Profiles
Collaborations and top research areas from the last five years
-
Large model and agents for face multi-granularity attribute analysis
Shen, L. (PI), Hou, X. (Team member) & xie, W. (Team member)
1/01/26 → 31/12/29
Project: Governmental Research Project
-
Text-Guided Face Image Generation and Local Attribute Editing with StyleGAN
Hou, X. (PI)
1/01/24 → 31/12/26
Project: Internal Research Project
-
Text-driven Controllable Face Generation and Local Attribute Editing
Hou, X. (PI)
1/01/23 → 31/12/25
Project: Governmental Research Project
-
A codebook-driven approach for low-light image enhancement
Wu, X., Hou, X., Lai, Z., Zhou, J., Zhang, Y. N., Pedrycz, W. & Shen, L., 15 Sept 2025, In: Engineering Applications of Artificial Intelligence. 156, 111115.Research output: Contribution to journal › Article › peer-review
Open Access11 Citations (Scopus) -
CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation
Xie, J., Deng, S., Hou, X., Luo, Z., Shen, L., Huang, Y., Zheng, Y. & Shou, M. Z., Aug 2025, In: International Journal of Computer Vision. 133, 8, p. 5569-5588 20 p.Research output: Contribution to journal › Article › peer-review
1 Citation (Scopus) -
DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing
Wang, X., Hou, X., Ding, M., Chen, J., Deng, K., Xie, J. & Shen, L., 27 Oct 2025, MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025. Association for Computing Machinery, Inc, p. 4020-4029 10 p. (MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025).Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review
Open Access1 Citation (Scopus) -
FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs
Wang, X., Ma, X., Hou, X., Ding, M., Li, Y., Chen, J., Chen, W., Peng, X. & Shen, L., 2025, In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. p. 9154-9164 11 p.Research output: Contribution to journal › Conference article › peer-review
2 Citations (Scopus) -
FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs
Wang, X., Ma, X., Hou, X., Ding, M., Li, Y., Chen, J., Chen, W., Peng, X. & Shen, L., 2025, Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025.Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review
-
-
Text-to-Image Personalization based on Diffusion Models
Hou, X. (Supervisor)
Jul 2024 → Sept 2024Activity: Supervision › Completed SURF Project