Avatar

Zhenyu Zhao

dwightzzy AT gmail.com

Lecturer

National University of Defence Technology

Biography

I am a lecturer at College of Liberal Arts and Sciences, National University of Defense and Technology. My research interests include computer vision, pattern recognition and machine learning. I had been a visiting PhD student at Peking University in Lin’s Lab during 2013-2015. I received the B.S. degree in mathematics from University of Science and Technology of China in 2009, and the Ph.D. degree in applied mathematics from National University of Defense and Technology in 2016.

Interests

  • Computer Vision
  • Machine Learning
  • Mathematical Statistics

Education

  • Phd in Applied Mathematics, 2012-2016

    National University of Defence Technology

  • MSc in System Science, 2009-2011

    National University of Defence Technology

  • BSc in Mathematics, 2005-2009

    University of Science and Technology of China

Publications @ZERO Lab

Feature Learning via Partial Differential Equation with Applications to Face Recognition. PR, 2017.

We propose a novel Partial Differential Equation (PDE) based method for feature learning. The feature learned by our PDE is …

Relaxed Majorization-Minimization for Non-smooth and Non-convex Optimization. AAAI, 2016.

We propose a new majorization-minimization (MM) method for non-smooth and non-convex programs, which is general enough to include the …

A Fast Alternating Time-Splitting Approach for Learning Partial Differential Equations. Neurocomputing, 2015.

We propose a new algorithm, called fast alternating time-splitting approach (FATSA), to solve the linear combination coefficients.

A Robust Hybrid Method for Text Detection in Natural Scenes by Learning-based Partial Differential Equations. Neurocomputing, 2015.

We present a robust hybrid method that uses learning-based PDEs for detecting texts from natural scene images.