As announced earlier, Jeremie Zumer will tell us about the human action recognition using deep learning tomorrow at the usual place. See below for the details.
Best,
- Cho
=== Speaker: Jeremie Zumer Date and Time: 28 Aug 2014 @13.30
Place: AA3195
Title: Deep Learning in Human Action Recognition
Abstract:
Hand-crafted features currently achieve state-of-the-art performance in human action recognition. As an undergraduate intern, I worked with Aaron Courville's team and investigated the application of neural-network-based models and deep architectures to this problem. During this talk, I will present some of the results of this project.