AI & Fundamentals

Playing with Visual AI - Helge Rhodin, Assistant Professor, UBC

Please register for this event here.

Abstract:

I will be talking about my past and ongoing work on human and animal capture: telepresence (virtual reality), injury prevention in sports (alpine skiing and soccer), behavioral classification in neuroscience (on Drosophila), visualizing sounds (to overcome hearing deficits), and using ultrasound for echolocation of persons (an alternative capture modality). I will also discuss inherent privacy issues with video surveillance and what we can do about it. Methodologically, I am playing with combinations of classical geometric computer vision and the most recent deep learning techniques. It is my goal to make machines learn to see from mere observation instead of laborious manual annotation---visual AI, a step towards general AI?

Bio:

Helge Rhodin is an Assistant Professor at UBC, associated with the computer vision and graphics labs. Prior to that, he was a lecturer at EPFL and postdoctoral researcher in Pascal Fua's CVLab. His research interests range from computer graphics and augmented reality, over 3D computer vision, to machine learning. Helge received the BSc and MSc degree in Computer science from Saarland University, respectively supervised by Philipp Slusallek and Sebastian Hack, and Michael Breuß and Joachim Weickert.  He graduated with a PhD in 2016, with his thesis on Motion Capture for Interactive Virtual Worlds, mentored by Christian Theobalt and Hans-Peter Seidel at the Max-Planck Institute for Informatics.

Please register for this event here.