Jan Kautz is VP of Learning and Perception Research at NVIDIA. Jan and his team pursue fundamental research in the areas of computer vision and deep learning, including visual perception, geometric vision, generative models, and efficient deep learning. Their work has been awarded various awards and has been regularly featured in the media. Before joining NVIDIA in 2013, Jan was a tenured faculty member at University College London. He holds an undergraduate degree in Computer Science (Universität Erlangen-Nürnberg), an MMath (University of Waterloo), a PhD degree (Max-Planck-Institut für Informatik), and worked as a post-doctoral researcher at the Massachusetts Institute of Technology.
AI for Perceiving Humans
Session Day and Time:
19 October 11:15am-12:15pm
Perceiving humans, such as their pose, gaze, etc., of great interest for many practical applications, including human-machine interaction, activity recognition, video analytics, visual effects, gaming, and any other application involving humans in the scenes. I'll present a our work focusing on a detailed understanding of the human body from monocular RGB images. Specifically, I'll present deep learning methods for body pose estimation, hand pose estimation, fiducial landmark detection, and eye gaze estimation and redirection. We'll show how deep learning models can be made robust to face challenges posed by real-world scenarios and address the problem of data scarcity for training these methods.