Abstract. We consider the problem of simultaneously registering several images to a 3D model. We propose a global approach based on mutual information that extends previous methods...
We propose a novel approach for shape-based segmentation based on a specially designed level set function format. This format permits us to better control the process of object re...
This paper presents a method for incrementally segmenting images over time using both intensity and motion information. This is done by formulating a model of physically signi cant...
Words in Chinese text are not naturally separated by delimiters, which poses a challenge to standard machine translation (MT) systems. In MT, the widely used approach is to apply ...
Jia Xu, Jianfeng Gao, Kristina Toutanova, Hermann ...
In this paper we propose a novel Conditional Random Field (CRF) formulation for the semantic scene labeling problem which is able to enforce temporal consistency between consecuti...