Signal Processing

On Wednesday, October 7, 2020 at 2:00 p.m., Dr. Ehsan Kamalinejad will present “GPT-3 for Vision”. Day & Time: Wednesday, October 7, 2020 2:00 p.m. – 3:00 p.m. Speaker: Ehsan Kamalinejad, PhD Co-Founder & CTO at Visual One Associate Professor at Cal State East Bay University Former Senior Machine Learning Scientist at Apple San Francisco, USA Organizer: IEEE Toronto Signal Processing Chapter Location: Virtual – Click here for the Google Meets link. Contact: Mehrnaz Shokrollahi Abstract: Deep learning in computer vision (CV) has proved to be very effective in solving many problems in real world. However, while the raw number of researches done in standard CV problems (such as ImageNet object classification/detection) has exploded, the measurable progress in these fields has slowed down. Additionally, there are many real-world problems in vision that are simply not compatible with the current approaches. This demands a new wave of problem statements in CV (and a new set of benchmarks). This talk focuses on one important set of such problem statements. We propose that many real-world problems in vision are “event recognition” problems. We introduce a concrete definition for the event recognition problem. We will see that this definition of event detection prohibits large sample sets. Hence, these events need to be recognize based on very few samples. We start by reviewing the current literature and we propose some promising directions for approaching this problem. At the end we show some demos from our recent effort on wrestling with this very challenging problem. Our solution can be best described by the “vision counterpart of GPT-3 few shot learner”. Register: Please check back soon for the registration link. Biography: Ehsan Kamalinejad (EK) is a senior machine learning engineer. He is currently working on Visual One which is a YCombinator backed startup he co-founded. Before that he was working for several years at Apple and Amazon as a staff machine learning engineer. Ehsan holds a faculty position as an associate professor at Cal State East Bay University. He got his PhD from University of Toronto. He has more than 7 years of experience delivering machine learning products in computer vision and natural language processing. His current project, Visual One, is about bringing next level intelligence to surveillance cameras.

On Friday, November 20, 2020 at 2:30 p.m., Mehrdad Fatourechi will present “Machine Learning and Digital Signal Processing Applications in Online Video Platforms”. Day & Time: Friday, November 20, 2020 2:30 p.m. – 4:00 p.m. Speaker: Mehrdad Fatourechi, PhD Organizer: IEEE Signal Processing Chapter Toronto Section Location: This event will be hosted on google meets Meeting ID meet.google.com/yej-opbp-uxo Phone Numbers (US)+1 617-675-4444 PIN: 974 200 026 6220# Contact: Mehrnaz Shokrollahi Abstract: In the past 15 years, we have seen exponential growth in online video platforms such as YouTube, Instagram, Netflix, TikTok, amongst others. In this talk, we will look at some of the challenges these platforms have been facing and how machine learning and digital signal processing are playing important roles in addressing these challenges. We will focus on discussing 3 areas: 1- Content discovery and SEO optimization 2- Establishing trust and safety, and 3- Protecting the rights of the content owners We will also discuss some of the areas that are currently open for future research. Register: Registration is not required. Biography: Mehrdad is the VP of Engineering of BroadbandTV, a media-tech company that is advancing the world through the creation, distribution, management, and monetization of content. Mehrdad is currently responsible for managing the research and development (R&D) and IT departments. When he joined BBTV in March 2010, he was initially responsible for managing the research team, and then his role later expanded to lead the entire engineering department. Under his leadership, BBTV’s tech team has become one of the leading and most innovative teams in digital video space, building several internal and external products (including VISO Catalyst, VISO Collab, VISO Prism, VISO NOVI, and VISO Mine) as well as filing several patents. Mehrdad has an in-depth knowledge of digital signal processing, machine learning, and pattern recognition algorithms. He holds a PhD in Electrical Engineering from the University of British Columbia (UBC), where he was nominated for NSERC’s Doctoral Prize Award. He is an author on more than 30 journal and conference papers with a focus on pattern recognition, machine learning and intelligent algorithms. He previously held positions in the tech/education industry including roles as a research associate and sessional lecturer at UBC, as well as consulting with several companies (INETCO, BC Mining Research, and STC enterprises). He was the co-chair of the IEEE Signal Processing Chapter in Vancouver for two years.

This talk will focus on the role of digital technology in providing a more patient-centric and proactive healthcare system. Following a motivational introduction to wearables and their role in providing a connected digital healthcare system, specific requirements for signal analysis and machine learning would be expanded. Case study examples of some of the innovation projects in the areas of baby heart rate monitoring, continuous vital signs analysis and mental health applications will be mentioned as the translational aspects of the research and development done at the Signal Analysis Research Lab in Toronto Metropolitan University. Speaker(s): Dr. Sri Krishnan, Room: ENGLG24, Bldg: George Vari Engineering and Computing Centre, ENG, 245 Church St, Toronto, Ontario, Canada, M5B 1Z4

This seminar will cover topics including: - Devices for Blind People, Amputees, People with Severe Disability - Control of Appliances Through sEMG and EOG, Rehabilitation Through Serious Games - Use of Internet of Things (IoT) for Human Activity Recognition (HAR) Based on Convolutional Neural Network (CNN) - Robots for Interaction with Children with ASD and Down Syndrome - Respiratory Rate Estimation Through Deep Learning Applied to Photoplethysmogram - COVID Detection Through Recurrent Neural Networks (RNN) and Deep Learning (DL) - Several Applications with Brain-Computer Interfaces (BCIs) Based on Electroencephalography (EEG) Speaker(s): Dr. Teodiano Freire Bastos-Filho, Room: 105, Bldg: Eric Palin Hall (EPH), 87 Gerrard St E, Toronto, Ontario, Canada, M5B 2M2