Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...
We describe an approach to segmenting foreground regions corresponding to a group of people into individual humans. Given background subtraction and ground plane homography, hierar...
Zhe Lin, Larry S. Davis, David S. Doermann, Daniel...
Inspired by the idea of multi-view, we proposed an image segmentation algorithm using co-EM strategy in this paper. Image data are modeled using Gaussian Mixture Model (GMM), and t...
Zhenglong Li, Jian Cheng, Qingshan Liu, Hanqing Lu
Network Mobility (NEMO) and IPv6 over Low power Wireless PAN (6LoWPAN) protocols are the two significant important technologies in the current networking research areas and seem to...
The objective of this paper is classifying images by the object categories they contain, for example motorbikes or dolphins. There are three areas of novelty. First, we introduce ...