When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
This paper introduces a new stochastic surface model for deformable 3D surfaces and demonstrates its utility for the purpose of 3D sculpting. This is the problem of simple-touse a...
Andrew R. Willis, Jasper Speicher, David B. Cooper
We present a latent hierarchical structural learning method for object detection. An object is represented by a mixture of hierarchical tree models where the nodes represent objec...
Leo Zhu, Yuanhao Chen, Antonio Torralba, Alan Yuil...
Simulations for training and analysis incorporating haptic feedback are becoming more popular and the sophistication of these simulations is increasing. Many systems now allow a r...
Abstract--A deformable registration method is proposed for registering a normal brain atlas with images of brain tumor patients. The registration is facilitated by first simulating...
Evangelia I. Zacharaki, Dinggang Shen, Seung-koo L...