

Lei Gao
Biography
Lei Gao is currently with the Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University. His research interests include multimodal machine learning, interpretable artificial intelligence, computer vision, and multimedia computing. He is a recipient of the Best Paper of 2021 IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR), the Best Student Paper of 2018 IEEE International Symposium on Multimedia (ISM), the Visiting Fellowship from Microsoft Research Asia (MSRA) in 2016, the Top 10% Papers Award of 2015 IEEE International Conference on Image Processing (ICIP). He is the associate editor of IECE Transactions on Multimedia Computing and is/was guest editor on some journals, such as ACM Transactions on Multimedia Computing,
Communications , and Applications, Frontiers in Remote Sensing, etc.


My Channel
My Channel


Piloted Driving

Pedestrian Detection with Deep Learning

Human-Computer Interface

Face Detection

Education
2018 - Present
Ryerson University
Post-Doctoral Fellow, Electrical & Computer Engineering
​
2013 - 2017
Ryerson University
PhD of Electrical & Computer Engineering
​
​
2008 - 2011
Zhengzhou University
Master of Communication and Information Engineering
​
​
2003 - 2007
Zhengzhou University
Bachelor of Physical Engineering
Research Interests
AWARDS AND HONOURS
​
The Best Student Paper in 20th IEEE International Symposium on
Multimedia
​
The Nominee for 2018 Young Investigator Prize
​
The Visiting Fellow at Microsoft Research Asia
Top 10% Papers Award, IEEE Int. Conf. on Image Processing 2015
​
Ryerson International Student Scholarship
The Access to Opportunity Program of Ryerson University
The National Scholarship of China
​
The Excellent Graduate Research Award of Ryerson University
​

Research Interests
Machine Learning
Big Data, Neural networks, Deep Learning, Discriminative Learning, Data Representation and Analysis
Computer Vision
Object Recognition, Tracking, Object Detection, Action Recognition
​
Pattern Recognition
Feature Extraction, Discriminant Representation
​
Multi-modal Information Fusion
​
​