Shiqi Wang

alt text 

Professor
Associate Dean for College of Computing
Dept. of Computer Science
City University of Hong Kong
Research Interest: Video Compression and Quality Assessment, Semantic and Visual Communications, Information Forensics and Security

Email: shiqwang@cityu.edu.hk
  

Biography

Shiqi Wang is a Professor of Computer Science, and serves as the Associate Dean for College of Computing at the City University of Hong Kong. He holds a Ph.D. (2014) from the Peking University under the supervision of Prof. Wen Gao and a B.Sc. in Computer Science from the Harbin Institute of Technology (2008). Before his current appointment, from Mar. 2014 to Mar. 2016, he was a Postdoc Fellow with the Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Canada. From Apr. 2016 to Apr. 2017, He was with the Rapid-Rich Object Search Laboratory (ROSE), Nanyang Technological University, Singapore, as a Research Fellow.

His primary research interests include video compression and quality assessment, semantic and visual communications, and information forensics and security. His current research focuses on the efficient representation of visual data for both human and AI systems, guided by the three S’s: Smart, Small, and Safe. Recognizing data as the foundation of AI, he develops algorithms for its efficient and reliable assessment, representation, compression, transmission, and utilization. His research has received more than 20,000 citations on Google Scholar. Together, these efforts advance efficient and trustworthy data representation and communication for applications involving humans, robots, and scientific research.

Representative Publications

[Google Scholar]

Note: Postdoctoral researchers, PhD students, and research assistants are shown in bold; corresponding authors are underlined.

Hybrid Video Coding

Extended coding unit partitioning for future video coding
Extended Coding Unit Partitioning for Future Video Coding
Meng Wang, Junru Li, Li Zhang, Kai Zhang, Hongbin Liu, Shiqi Wang, Sam Kwong, and Siwei Ma,
IEEE Transactions on Image Processing, 2019.

How can we achieve more flexible block partitioning beyond quad-tree plus binary-tree for future coding? The proposed extended coding unit partitioning technologies have been adopted by the AVS3 standard.

Can LLMs design video coding tools? A case study on planar mode
Can LLMs Design Video Coding Tools? A Case Study on Planar Mode
Yingwen Zhang, Meng Wang, Liqiang He, Shiqi Wang,
IEEE International Conference on Visual Communications and Image Processing, 2026.

We show that LLMs are capable not only of writing code but also of designing video coding tools/algorithms, with very promising performance.

Dependent learned rate-distortion optimization
A Theoretical and Experimental Study for Dependent Learned Rate-Distortion Optimization
Yingwen Zhang, Meng Wang, Junru Li, Kai Zhang, Li Zhang, and Shiqi Wang,
IEEE Transactions on Circuits and Systems for Video Technology, 2025.

We revisit the dependency issue in intra coding through a probabilistic framework and aim to tap the full potential of dependent learned RDO.

Generative Coding

Compact temporal trajectory representation for talking face video compression
Compact Temporal Trajectory Representation for Talking Face Video Compression
Bolin Chen, Zhao Wang, Binzhe Li, Shiqi Wang, Yan Ye,
IEEE Transactions on Circuits and Systems for Video Technology, 2023.

We propose a generative face video coding method that achieves superior rate-distortion performance over state-of-the-art codecs. Beyond compression gains, this work contributed to JVET’s first standardization activity on generative video coding, where a SEI-based specification was developed to encapsulate compact features for generative face video compression.

CompGS: efficient 3D scene representation via compressed Gaussian splatting
CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting
Xiangrui Liu, Xinju Wu, Pingping Zhang, Shiqi Wang, Zhu Li, Sam Kwong,
ACM International Conference on Multimedia, 2024.

We propose CompGS, a compact 3D Gaussian representation framework that combines predictive coding and rate-constrained optimization to reduce storage overhead while preserving high-quality rendering.

Cross-modality video compression with multimodal large language models
When Video Compression Meets Multimodal Large Language Models: A Unified Paradigm for Cross-Modality Video Compression
Pingping Zhang, Jinlong Li, Kecheng Chen, Meng Wang, Long Xu, Haoliang Li, Nicu Sebe, Sam Kwong, and Shiqi Wang,
IEEE Signal Processing Letters, 2026.

We show that simply use multimodal LLM as the decoder can significantly improve the coding performance.

Quality Assessment

Deep recursive band network for low-light image enhancement
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement
Wenhan Yang, Shiqi Wang, Yuming Fang, Yue Wang, and Jiaying Liu,
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.

Fidelity and perceptual quality often trade off against each other. How to jointly optimize these two objectives within a perceptual quality optimization framework is an important problem.

Patch-based contrast quality index for contrast changed images
A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images
Shiqi Wang, Kede Ma, Hojatollah Yeganeh, Zhou Wang, and Weisi Lin,
IEEE Signal Processing Letters, 2015.

We propose a local patch-based objective quality assessment method based on an adaptive representation of local patch structure. The resulting local contrast quality map can predict spatial variations in local quality.

DISTS model unifying structure and texture similarity
Image Quality Assessment: Unifying Structure and Texture Similarity
Keyan Ding, Kede Ma, Shiqi Wang, and Eero P. Simoncelli,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.

The proposed DISTS has been widely used in various applications, including image compression, restoration, and medical imaging.

Academic Services

Past and Current Editorial Services

Journal Reviewer

Technical Activity

Services in International Conferences

Special Session Organizer

Selected Honors

Contact Information