- This event has passed.
Spring 2024 GRASP SFI: Andrew Owens, University of Michigan, “Multimodal Learning from the Bottom Up”
February 7 at 10:30 AM - 11:30 AM
This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom.
Today’s machine perception systems rely extensively on supervision provided by humans, such as natural language. I will talk about our efforts to make systems that, instead, learn from two ubiquitous sources of unlabeled sensory data: visual motion and cross-modal associations between senses. First, I will discuss our work on creating unified self-supervised motion analysis methods that can address both object tracking and optical flow tasks. I will then discuss how these same techniques can be applied to localizing sound sources in video, and how tactile sensing data can be used to train multimodal visual-tactile models. Finally, I will talk about our recent work on subverting visual perception systems, by creating “multi-view” optical illusions: images that change their appearance under a transformation, such as a flip or rotation.
University of Michigan
Andrew Owens is an assistant professor at The University of Michigan in the department of Electrical Engineering and Computer Science. Prior to that, he was a postdoctoral scholar at UC Berkeley. He received a Ph.D. in Electrical Engineering and Computer Science from MIT in 2016. He is a recipient of a Computer Vision and Pattern Recognition (CVPR) Best Paper Honorable Mention Award.