— Reinforcement learning (RL) algorithms have long been promising methods for enabling an autonomous robot to improve its behavior on sequential decision-making tasks. The obviou...
Abstract-- Many applications are driven by evolving data -patterns in web traffic, program execution traces, network event logs, etc., are often non-stationary. Building prediction...
Shixi Chen, Haixun Wang, Shuigeng Zhou, Philip S. ...
We propose a novel approach to reconstruct complete
3D deformable models over time by a single depth camera,
provided that most parts of the models are observed by the
camera at...
We1 present a new method to shape-based segmentation of deformable anatomical structures in medical images and validate this approach by detecting and tracking the endocardial bor...
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...