Topic：Probabilistic Models for Video Segmentation Time：2016年1月25日（周一）下午2:00 - 3:30 Venue：信电大楼-215学术厅 Speaker：Dr. Michael Ying Yang, Computer Vision Labe Dresden, Germany

Biography

Dr. Michael Ying Yang is currently a Senior Researcher at Computer Vision Lab Dresden (CVLD), TU Dresden, Germany. From 2012 to 2015, he was a postdoctoral research associate at the Institute for Information Processing (TNT), Leibniz University Hannover. He received his Ph.D. (summa cum laude) from University of Bonn in 2011. His research interests are in the areas of computer vision and photogrammetry, with focuses on probabilistic graphical models, multisensor fusion, and scene understanding.

Abstract

In Computer Vision, video segmentation is a challenging problem because it involves a large amount of data and object appearance may significantly change over time. In this talk, I will mainly introduce probabilistic models for video segmentation problem. Specifically, I will talk about a bottom-up approach for the combination of object segmentation and motion segmentation using a novel graphical model, which is formulated as inference in a conditional random field model. This model combines object labeling and trajectory clustering in a unified probabilistic framework. In the end of the talk, I will highlight some promising research directions in this area.