Abstract:
Modern technological advances produce data at breathtaking scales and complexities such as the images and videos on the web. Such big data require highly expressive models for their representation, understanding and prediction. To fit such models to the big data, it is essential to develop practical learning methods and fast inferential algorithms. In this talk, with emphasis on a vision restricted Turing test -- the grand challenge in computer vision, I will introduce my work on (i) Statistical Learning of Large Scale and Highly Expressive Hierarchical Models from Big Data, and (ii) Bottom-up/Top-down Inference with Hierarchical Models by Learning Near-Optimal Cost-Sensitive Decision Policies. Applications in object detection, online object tracking and robot autonomy will be discussed.

Biography:
Matt Tianfu Wu is currently a research assistant professor in the center for vision, cognition, learning and autonomy (VCLA) at University of California, Los Angeles (UCLA). He received a Ph.D. in Statistics from UCLA in 2011 under the supervision of Prof. Song-Chun Zhu. His research has been focused on statistical modeling, inference and learning, and computer vision: (i) Statistical learning of large scale and highly expressive hierarchical and compositional models from visual big data (images and videos). (ii) Statistical inference by learning near-optimal cost-sensitive decision policies. (iii) Statistical theory of performance guaranteed learning algorithm and optimally scheduled inference procedure.

Host:
Dr. Joyce Chai