Zengqun Zhao

Zengqun Zhao

PhD Student in Computer Science
Multimedia and Vision Research Group
School of Electronic Engineering and Computer Science
Queen Mary University of London
LinkedIn Google Scholar GitHub CV

About

I am currently a final-year PhD student in Computer Science at Queen Mary University of London (QMUL), working with Prof. Ioannis Patras and funded by the Queen Mary Principal's Scholarship. I am also fortunate to be collaborating closely with Dr. Ziquan Liu and Prof. Shaogang Gong. Previously, I obtained my MSc degree in Control Science and Engineering from Nanjing University of Information Science & Technology (NUIST), where I worked with Prof. Qingshan Liu.

My research background spans human facial behaviour understanding and vision-language models. Currently, I focus on video generation with diffusion models.

Outside of research, I am passionate about music, particularly rock music, spanning progressive rock, post rock, Britpop, gothic rock, funk rock, and shoegaze. I enjoy playing guitar and singing. I also love staying active through hiking, cycling, and fitness.

Publications

Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
Zengqun Zhao, Yanzuo Lu, Ziquan Liu, Jifei Song, Jiankang Deng, Ioannis Patras
arXiv, 2026
PDF Code / Models Project Page
LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
Zengqun Zhao, Ziquan Liu, Yu Cao, Shaogang Gong, Zhensong Zhang, Jifei Song, Jiankang Deng, Ioannis Patras
arXiv, 2026
PDF Code / Models Project Page
AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data
Zengqun Zhao, Ziquan Liu, Yu Cao, Shaogang Gong, Ioannis Patras
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
PDF Code / Models Project Page
Temporal Score Analysis for Understanding and Correcting Diffusion Artifacts
Yu Cao, Zengqun Zhao, Ioannis Patras, Shaogang Gong
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
PDF Code / Models Project Page
2026
Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
Zengqun Zhao, Yanzuo Lu, Ziquan Liu, Jifei Song, Jiankang Deng, Ioannis Patras
arXiv, 2026
PDF Code / Models Project Page
LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
Zengqun Zhao, Ziquan Liu, Yu Cao, Shaogang Gong, Zhensong Zhang, Jifei Song, Jiankang Deng, Ioannis Patras
arXiv, 2026
PDF Code / Models Project Page
2025
AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data
Zengqun Zhao, Ziquan Liu, Yu Cao, Shaogang Gong, Ioannis Patras
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
PDF Code / Models Project Page
Temporal Score Analysis for Understanding and Correcting Diffusion Artifacts
Yu Cao, Zengqun Zhao, Ioannis Patras, Shaogang Gong
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
PDF Code / Models Project Page
Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer
Zengqun Zhao, Yu Cao, Shaogang Gong, Ioannis Patras
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025 Oral
PDF Code / Models
2023
Prompting Visual-Language Models for Dynamic Facial Expression Recognition
Zengqun Zhao, Ioannis Patras
British Machine Vision Conference (BMVC), 2023
PDF Code / Models
2021
Former-DFER: Dynamic Facial Expression Recognition Transformer
Zengqun Zhao, Qingshan Liu
ACM International Conference on Multimedia (ACM MM), 2021
PDF Code / Models
Learning Deep Global Multi-Scale and Local Attention Features for Facial Expression Recognition in the Wild
Zengqun Zhao, Qingshan Liu, Shanmin Wang
IEEE Transactions on Image Processing (TIP), 2021
PDF Code / Models
Robust Lightweight Facial Expression Recognition Network with Label Distribution Training
Zengqun Zhao, Qingshan Liu, Feng Zhou
AAAI Conference on Artificial Intelligence (AAAI), 2021
PDF Code / Models

Experiences

Research Intern
London Research Center, Huawei R&D UK
Apr 2025 – Mar 2026
  • Worked on video diffusion models.
Teaching Assistant
Queen Mary University of London
Jan 2023 – Apr 2025
  • Machine Learning (Autumn 2023, 2024) — Module Lead: Prof. Ioannis Patras
  • Deep Learning and Computer Vision (Spring 2024, 2025) — Module Lead: Prof. Shaogang Gong
University College London
Jan 2024 – Mar 2024
  • Affective Computing and Human-Robot Interaction — Module Lead: Prof. Nadia Berthouze
Research Intern
DAMO Academy, Alibaba Group
Jul 2021 – Sep 2021
  • Worked on lightweight face detection and recognition.