In this paper, we propose a novel graph embedding method for the problem of lipreading. To characterize the temporal connections among video frames of the same utterance, a new di...
In this paper, an unsupervised learning algorithm, neighborhood linear embedding (NLE), is proposed to discover the intrinsic structures such as neighborhood relationships, global ...
Shuzhi Sam Ge, Feng Guan, Yaozhang Pan, Ai Poh Loh
Scripting is a powerful, high-level, cross-platform, dynamic, easy way of composing software modules as black boxes. Unfortunately, the high runtime overhead has prevented scripti...
We propose a novel approach for improving level set seg-
mentation methods by embedding the potential functions
from a discriminatively trained conditional random field
(CRF) in...
Dana Cobzas (University of Alberta), Mark Schmidt ...
This paper considers a recently proposed method for unsupervised learning and dimensionality reduction, locally linear embedding (LLE). LLE computes a compact representation of hi...