Parham Aarabi's University of Toronto Website

Professor Parham Aarabi
Department of Electrical and Computer Engineering, University of Toronto
(External affiliation: President and CEO at ModiFace Inc.)

Bio: Ph.D. (Elec. Eng.) from Stanford in 2001. UofT Professor since 2001. Undergrad degree from UofT in Engineering Science (1998) and M.A.Sc. from UofT (1999). Published over 100 peer-reviewed papers, won a few research/teaching awards including the IEEE Mac Van Valkenburg Early Career Teaching Award, the Gordon R. Slemon Teaching of Design Award, the ECE Professor of the Year award, the Premier's Catalyst Award for Innovation, the Canada Research Chair, and MIT's TR35 "Top Young Innovator" award.

My Most Famous (+Awesome) Group Alumni

Dr. Alireza Rabi - MD/PhD from John's Hopkins - The most brilliant, humble, and well-rounded person I have ever met

Dr. Guangji Shi - Senior Audio R&D Engineer at DTS Inc. - My first Ph.D. Student!!!

Dr. Steven Rennie - Research Scientist at IBM Research - My old friend and star researcher at IBM

Dr. Omid Jahromi - Sr. Machine Learning Engineer at Belkin

Dr. Maryam Modir Shanechi - PhD from MIT

Dr. Sam Mavandadi - Post Doctoral Scholar at UCLA

Dr. Nevena Lazic - Researcher at Microsoft Research

Dr. Bob Mungamuru - Vice President at Goldman Sachs

Sarah Ali - Director of Product at Achievers

Alborz Mahdavi - PhD candidate at CalTech

Alexander Karpenko - PhD candidate at Stanford - This is the person who will one day create the next Google!

Ron Appel - PhD candidate at CalTech - Most energetic student I have ever had. Will do amazing things .. as long as he cuts down his Coke drinking ;)

Amin Heidari - Director of R&D at ModiFace

Arezou Keshavarz - PhD candidate at Stanford

Tommy Liu - PhD Candidate at Carnegie Mellon

Research Spotlight

Here are a few recent papers from our lab:

Amin Heidari, Parham Aarabi: Real-Time Object Tracking on iPhone. ISVC (1) 2011: 768-777

A novel real-time object tracking algorithm is proposed which tracks objects in real-time on an iPhone platform. The system utilizes information such as image intensity, color, edges, and texture for matching different candidate tracks. The tracking system adapts to changes in target appearance and size (including resizing candidate tracks to a universal depth-independent size) while running at 10-15FPS tracking rate. Several experiments conducted on actual video are used to illustrate the proposed approach.

Alexandre Karpenko, Parham Aarabi: Tiny Videos: A Large Data Set for Nonparametric Video Retrieval and Frame Classification. IEEE Trans. Pattern Anal. Mach. Intell. 33(3): 618-630 (2011)

In this paper, we present a large database of over 50,000 user-labeled videos collected from YouTube. We develop a compact representation called 'tiny videos' that achieves high video compression rates while retaining the overall visual appearance of the video as it varies over time. We show that frame sampling using affinity propagation - an exemplar-based clustering algorithm - achieves the best trade-off between compression and video recall. We use this large collection of user-labeled videos in conjunction with simple data mining techniques to perform related video retrieval, as well as classification of images and video frames. The classification results achieved by tiny videos are compared with the tiny images framework for a variety of recognition tasks. The tiny images data set consists of 80 million images collected from the Internet. These are the largest labeled research data sets of videos and images available to date. We show that tiny videos are better suited for classifying scenery and sports activities, while tiny images perform better at recognizing objects. Furthermore, we demonstrate that combining the tiny images and tiny videos data sets improves classification precision in a wider range of categories.