题目：Learning Visual Models for Human Pose Estimation in Images
Parsing human poses in images is fundamental in extracting critical visual information for artificial intelligent agents. In this talk I will present our recent approach to learn self-contained body part representations from images, and their part-wise geometric contexts in this parsing process. The concept of “self-containedness” refers to (i) self-contained unit must have a limited complexity, such that (ii) information appears in geometric contexts appropriate for recognition, and (iii) the representation can be processed fiexibly.
In our approach, each symbol is individually learned by categorizing visual features leveraged by geometric information. In the categorization, we use Latent Support Vector Machine followed by an efficient cross validation procedure to learn visual symbols. Then, these symbols naturally define geometric contexts of body parts in a fine granularity. When the structure of the compositional parts is a tree, we derive an efficient approach to estimating human poses in images.
This work is primarily sponsored by Bionic Eye, a special initiative of Australian Government through Australian Research Council. We will present in the International Joint Conference on Artificial Intelligence in Beijing. A preliminary version of the paper is available http://arxiv.org/pdf/1304.6291v1.pdf
Dr. Yi Li received his Ph.D from the ECE Dept. at the University of Maryland at College Park in 2011. His PhD research, entitled “Cognitive Robots for Social Intelligence”, focus on visual navigation for mobile robots, optical motion capture, causal inference for coordinated groups, and action recognition and representation. He was the recipient Future Faculty Fellow at Maryland from 2008-2010, received the Best Student paper of ICHFR, and the second price in the Semantic Robot Vision Challenge (SRVC). He joined NICTA as a Researcher since 2011 in the Visual Processing for Bionic Eye (VIBE) project, and developed algorithms for visualizing critical information (US/AU patents pending). His recent research interests include human pose estimation, higher order loss function in machine learning, and image deblurring via sparse signal processing.