Carnegie Mellon University

Advanced Search   
  Look in
       Title    Full-text
  Date Range
VASC Seminar: Xiaoyu Ding
Facial Action Unit Event Detection by Cascade of Tasks

Xiaoyu Ding
Visiting Scholar RI, Carnegie Mellon University

November 18, 2013

Automatic facial Action Unit (AU) detection from video is a long-standing problem in facial expression analysis. AU detection is typically posed as a classification problem between frames or segments of positive examples and negative ones, where existing work emphasizes the use of different features or classifiers. In this paper, we propose a method called Cascade of Tasks (CoT) that combines the use of different tasks (i.e., frame, segment and transition) for AU event detection. We train CoT in a sequential manner embracing diversity, which ensures robustness and generalization to unseen data. In addition to conventional framebased metrics that evaluate frames independently, we propose a new event-based metric to evaluate detection performance at event-level. We show how the CoT method consistently outperforms state-of-the-art approaches in both frame-based and event-based metrics, across three public datasets that differ in complexity: CK+, FERA and RU-FACS.

Additional Information

Host: Kris Kitani

Speaker Biography

Xiaoyu Ding is a visiting scholar in Robotics Institute, Carnegie Mellon University. He works with Fernando De la Torre and Jeffrey F. Cohn. His research interests include practical aspects of computer vision and machine learning. In particular, he is working on facial expression analysis in videos.