Mahdi Biparva

I am a PhD student in the Electrical Engineering and Computer Science department at York University, Toronto, Canada. I am a member of the Laboratory of Active and Attentive Vision (LAAV) and my supervisor is John Tsotsos. My PhD research focuses on visual attention in deep learning for recognition tasks such as classification, detection and segmentation. I am investigating various ways of integrating the Selective Tuning (ST) model of visual attention into the Convolutional Neural Networks (CNN).

I completed my Master's degree at Concordia University, Montreal, Canada in 2013. I was part of the Center for Pattern Recognition and Machine Intelligence (CENPARMI) and finished my program under the supervision of Ching Suen. I worked on probabilistic kernel models in handwritten recognition.

• Oct 2019, I presented my PhD research at Trailab, University of Toronto.
• Sept 2019, I presented my PhD research at Vision and Image Processing lab, University of Waterloo.
• Sept 2019, I presented my PhD research at Amazon Alexa, Toronto office.
• Sept 2019, I successfully defended my PhD thesis at York University.
• Sept 2018, I finished industrial internship at Huawei Noah's Ark (Computer Vision research engineer).
• Oct 2018, STNet code for object localization is available on Github.
• June 2018, Priming paper is presented at CVPR Workshop 2018
• Oct 2017, STNet paper is presented at ICCV Workshop 2017

• Advanced Inference Algorithms / Machine Learning (University of Toronto)
• Computer Vision (York University)
• Convex Optimization (York University)
• Advanced Image Processing (Concordia University)
• Machine Learning (Concordia University)
• Pattern Recognition (Concordia University)