Shishir K. Shah

Shishir K. Shah serves as Professor and Chair of the Department of Computer Science within the College of Natural Sciences and Mathematics at the University of Houston. His leadership extends to university-wide committees including Chair of the Undergraduate Committee of the Faculty Senate.

Education:

• B.S. in Mechanical Engineering, The University of Texas at Austin
• M.S. & Ph.D. in Electrical and Computer Engineering, The University of Texas at Austin

Professor Shah's research centers on computer vision fundamentals, specializing in machine learning and statistical methods for image/data analysis. His work addresses critical challenges in human behavior analysis, person re-identification under occlusion and clothing changes, video analytics, biometrics, and microscope image analysis. The Quantitative Imaging Laboratory he directs develops solutions for real-world surveillance, educational technology, and medical imaging applications.

His recent publications reveal strong focus trends in occlusion-robust person re-identification (addressing both clothing changes and visual obstructions) and educational video analytics. These works demonstrate innovative approaches using graph attention networks, cross-modality learning, and transformer architectures to solve persistent challenges in visual recognition.

Scientific Awards:

• John C. Butler Teaching Excellence Award (2011)
• Department of Computer Science Academic Excellence Award (2010, 2016)
• Student Vuong Dustin Nguyen received Dan E. Wells Outstanding Dissertation Award

Professor Shah actively mentors graduate students, with documented success in dissertation supervision. His research program includes significant grant activity supporting the Quantitative Imaging Laboratory. He serves as Associate Editor for Image and Vision Computing, IEEE Journal of Translational Engineering on Health and Medicine, and Pattern Recognition, demonstrating strong community engagement.

The Quantitative Imaging Laboratory operates at the intersection of theoretical computer vision research and practical applications, with projects spanning educational technology (Videopoints lecture video portal), surveillance systems, and biomedical imaging. Current work emphasizes robustness to real-world challenges like clothing changes, occlusions, and viewpoint variations in visual recognition systems.