PeopleofSuperintelligence

Researcher

Colin S. C. Tsang

Also known as Siu Chung Tsang

Colin Tsang is a researcher whose work connects mathematical optimization with deep learning for image analysis. He completes an undergraduate mathematics project at HKBU in 2013–2014, works there as a research assistant in 2014, and develops preconditioners for optimal-control problems in his master’s thesis in 2017. At HKUST, he presents a survey of deep-learning methods for medical-image super-resolution in 2022 and defends work on weakly supervised denoising and super-resolution in 2023. In 2025, he coauthors an MRNet+ paper on knee-MRI meniscus-tear diagnosis; in 2026, he coauthors a paper on SFTNet for lightweight deepfake detection. As of October 2026, he is a lecturer in the Department of Computer Science and Engineering at CUHK.

Timeline

  1. 2013–2014

    Undergraduate mathematics project

    During 2013–2014, he completes MATH 3591 Mathematical Science Project 1 in HKBU’s Department of Mathematics.

  2. 2014

    Research assistant at HKBU

    He works as a research assistant in HKBU’s Department of Mathematics in 2014.

  3. 2017

    Preconditioners for optimal control

    He earns a B.Sc. in Mathematical Sciences and an M.Phil. in Applied Mathematics at HKBU. In 2017, he completes an M.Phil. thesis on preconditioners for linear parabolic optimal-control problems under Wing Hong Felix Kwok.

  4. January 2022

    Medical-image super-resolution

    In January 2022, he presents a PhD qualifying examination in HKUST’s Department of Computer Science and Engineering on deep-learning approaches to medical-image super-resolution, with Albert Chung and Chi-Keung Tang as supervisors.

  5. June 2023

    Weakly supervised image restoration

    In June 2023, he defends a PhD thesis in HKUST’s Department of Computer Science and Engineering on medical-image denoising and super-resolution, supervised by Pedro Sander and Albert Chung. His weakly supervised joint method trains on one noisy high-resolution capture, and his Continuous Diffusion Model supports arbitrary-resolution reconstruction without training data.

  6. October 2025

    Diagnosis from knee MRI

    In October 2025, he coauthors “Advancing Meniscus Tear Diagnosis in Knee MRI: MRNet+” with J. H. Y. Lam and K. W. Sum for the 2025 IEEE International Conference on Systems, Man, and Cybernetics proceedings. The MRNet+ model achieves an AUC of 88.49% for meniscus-tear diagnosis.

  7. January 2026

    Lightweight deepfake detection

    In January 2026, he coauthors “Lightweight Deepfake Detection Application Using SFTNet” with C. S. Ip, H. L. Wong and K. W. Sum for the 2025 IEEE International Conference on Systems, Man, and Cybernetics proceedings. SFTNet combines spatial and frequency-domain features for deepfake-video detection.

  8. As of October 2026

    Lecturer at CUHK

    As of October 2026, he is a lecturer in the Department of Computer Science and Engineering at the Chinese University of Hong Kong. His research interests include deep learning, image analysis and scientific computing.

Career

  1. NowChinese University of Hong KongLecturer
  2. 2014Hong Kong Baptist UniversityResearch Assistant

Education

  1. 2023Hong Kong University of Science and TechnologyPhD
  2. Hong Kong Baptist UniversityB.Sc.; M.Phil.

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Chinese University of Hong Kong. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. Universities keep AI researchers for a median of 6 years, compared with 2 years at frontier labsIncludes Chinese University of Hong Kong. Across 15,811 dated work stays (6,529 people), median role tenure runs from 6 years at universities to 2 years at frontier labs. We compare all five organization types, starting decades from the 1970s to the 2020s, and the organizations that keep people longest.
  3. The United States employs an estimated 48% of people shaping AIIncludes Chinese University of Hong Kong. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Chinese University of Hong Kong. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Colin S. C. Tsang yet. Send us a free-licensed photo.

  1. Teaching | Henry Y.T. Ngan, Ph.D. 顏旭東博士 ytngan.wordpress.com. Checked 22 October 2026.
  2. Siu Chung TSANG - The Chinese University of Hong Kong research.cuhk.edu.hk. Checked 22 October 2026.
  3. Preconditioners for linear parabolic optimal control problems - Hong Kong Baptist University scholars.hkbu.edu.hk. Checked 22 October 2026.
  4. Medical Images Super-resolution by Deep Learning: A Survey | HKUST CSE cse.hkust.edu.hk. Checked 22 October 2026.
  5. DENOISING AND SUPER-RESOLUTION OF MEDICAL IMAGES BY WEAKLY AND SELF-SUPERVISED LEARNING | HKUST CSE cse.hkust.edu.hk. Checked 22 October 2026.
  6. Advancing Meniscus Tear Diagnosis in Knee MRI: MRNet+ - The Chinese University of Hong Kong research.cuhk.edu.hk. Checked 22 October 2026.
  7. Lightweight Deepfake Detection Application Using SFTNet - The Chinese University of Hong Kong research.cuhk.edu.hk. Checked 22 October 2026.