This paper proposes LTNC, a new recoding algorithm to build low complexity network codes. At the core of LTNC is a decentralized version of LT codes that allows the use of fast be...
Belief propagation (BP) is an effective algorithm for solving energy minimization problems in computer vision. However, it requires enormous memory, bandwidth, and computation beca...
Chao-Chung Cheng, Chia-Kai Liang, Homer H. Chen, L...
This paper describes the realization of a parallel version of the k/h-means clustering algorithm. This is one of the basic algorithms used in a wide range of data mining tasks. We ...
We present Propagation Networks (P-Nets), a novel approach for representing and recognizing sequential activities that include parallel streams of action. We represent each activi...
Yifan Shi, Yan Huang, David Minnen, Aaron F. Bobic...
We propose a statistical formulation for 2-D human pose estimation from single images. The human body configuration is modeled by a Markov network and the estimation problem is to...