Prototype classifiers trained with multi-class classification objective are inferior in pattern retrieval and outlier rejection. To improve the binary classification (detection, v...
In this paper, we present a systems approach for channel modeling of an Automatic Speech Recognition (ASR) system. This can have implications in improving speech recognition compo...
Qun Feng Tan, Kartik Audhkhasi, Panayiotis G. Geor...
Background subtraction is commonly used to detect foreground objects in video surveillance. Traditional background subtraction methods are usually based on the assumption that the...
The goal of emotion classification is to estimate an emotion label, given representative data and discriminative features. Humans are very good at deriving high-level representat...
Having effective methods to access the images with desired object is essential nowadays with the availability of huge amount of digital images. We propose a semantic higher-level ...
Ismail Elsayad, Jean Martinet, Thierry Urruty, Cha...