Structured Articulated Human Pose Estimation

ABSTRACT

Automatically understanding the body pose from camera inputs promotes many real-life applications such as human activity recognition, autonomous driving, assistant robotics and sport analysis. This highly demanding task has seen extraordinary progress over the recent years. The success can be credited to two main factors: effective appearance modeling by deep neural networks and the accessibility of large-scale annotated datasets. However, the current systems are not flawless that still many challenging issues are left to be alleviated especially when people are in complex articulations or several instances stay close, occluding each other. We argue that incorporating prior knowledge like the inherent structure of our body into the network design is equally essential. To this end, in this work, we study how to design efficient algorithms to jointly optimize the parameters of deep feature extractors and also the probabilistic inference models which encode priors.