We present a 2D model-based approach to localizing human body in images viewed from arbitrary and unknown angles. The central component is a statistical shape representation of th...
Despite the phenomenal growth of Internet users, the penetration rate of Internet shopping remains low. Previous works suggesting that the lack of trust is the major impediment st...
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
We simulate the evolution of a domain vocabulary in small communities. Empirical data show that human communicators can evolve graphical languages quickly in a constrained task (P...
A stochastic model is formulated and analyzed to study the advancements of messages under greedy routing in a sensor network with a power-saving scheme. The aim of this model is g...