About

Hello, my name is Li-Yun (James) Wang. I am a Ph.D. candidate in Computer Science at Portland State University (PSU). Before joining the Ph.D. program at PSU, I was supervised by Dr. Liang-Hua Chen and received my master’s degree from Fu Jen Catholic University, New Taipei, Taiwan, from 2010 to 2012. Since I was pursuing my M.S. degree, I passionate about computer vision problems such as object recognition, object detection, and image and video processing problems by leveraging image processing, computer vision, and machine learning techniques. During my Ph.D. journey, my research interest includes Computer Vision (CV) and Multimedia Computing (MC). Specifically, I would like to utilize machine learning and deep learning techniques to solve research problems in CV and MC. Specifically, I am passionate about the following research topics: Applications of Generative Adversarial Networks (GANs), Neural Network Model Compression, and Self-Supervised/Semi-Supervised Learning. As a Ph.D. student, it is my pleasure to have an opportunity to be able to work on cool projects with Dr. John Lipor, Dr. Aniket Anand Deshmukh, and Dr. Anthony Rhodes. The current projects I am working on are as follows:

Research Projects:
(1) Class Specialization Knowledge Distillation:

• Research and develop to make compact models for certain classification tasks

(2) Semi-Supervised Learning for Open-world Lifelong Learning/Classification Tasks:

• Research and develop semi-supervised learning approches.

Completed Projects:
(1) Adversarial Deep Learning:

• Research and develop new adversarial defense approaches to increase the robustness of Deep Convolutional Neural Networks.

(2) Video as Text: A New Paradigm for Video Processing:

• Research and develop a novel content-based video processing software tool.

(3) Image Deblurring via Generative Adversarial Networks:

• Research and develop new image deblurring approaches by GAN-based techniques.