Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...
Conventional image categorization techniques primarily rely on low-level visual cues. In this paper, we describe a multimodal fusion scheme which improves the image classification...
Abstract--This paper tackles a fundamental problem of network planning and dimensioning under EPON-WiMAX integration for next-generation wireless metropolitan-area broadband access...
Bin Lin, Pin-Han Ho, Xuemin Shen, Frank Chih-Wei S...
In this paper, based on the concept of the Tapped Delay Line (TDL) structure, we first propose a new wideband multiple-ring Multiple Input Multiple Output (MIMO) channel reference ...
This paper presents a method for learning 3D object templates from view labeled object images. The 3D template is defined in a joint appearance and geometry space, and is compose...