About the Session
The session will introduce the fundamentals of computer vision and feature engineering. Activities emphasize that machine perception is a difficult problem and that while manual approaches are effective for many tasks, they aren’t always appropriate for complex real-world tasks. Through hands-on practices, participants will understand the properties of fundamental visual features and their implications for perceptual processing.
Dr. Sharifa Alghowinem
Sharifa Alghowinem is a visiting scholar at the Personal Robots Group at the MIT Media Lab, where she works on AI modeling for computer vision, audio and signal processing. She received her M.Sc. and Ph.D in computer science from Australian National University in 2010 and 2015, specializing in multimodal AI. Her research expertise is on multimodal automatic recognition of human mood and behaviours, such as diagnoses of depression and multi-person interaction analysis, through combining and analyzing behavioural modalities such as speech, eye gaze, head and body gestures. She is also an assistant professor, and the associate director of postgraduate programs at Prince Sultan University in Saudi Arabia. She will be leading the machine vision and supervised learning sessions of the course.