Stephen Moore

Learn More
This paper introduces a novel approach to facial expression recognition in video sequences. Low cost contour features are introduced to effectively describe the salient features of the face. Temporalboost is used to build classifiers which allow temporal information to be utilized for more robust recognition. Weak classifiers are formed by assembling edge(More)
In this paper, we present a method to assist users in selecting quality parameters for streaming video. Constrained scaling, a method for calibrating users' subjective judgements to a naturalistic scale is introduced. An experiment in which participants judged the fluidity of sample videos across different frame rates demonstrates the effectiveness of(More)
Over the last two decades automatic facial expression recognition has become an active research area. Facial expressions are an important channel of non-verbal communication, and can provide cues to emotions and intentions. This paper introduces a novel method for facial expression recognition, by assembling contour fragments as discriminatory classifiers(More)
A new type of independent practice association has been organized to encourage primary-care physicians in private practice to become coordinators and financial managers for all medical care. Each patient chooses one internist, family or general physician or pediatrician and must be referred by that physician for all specialized care. The primary-care(More)
BACKGROUND Increasing emphasis on integrated control of neglected tropical diseases (NTDs) requires identification of co-endemic areas. Integrated surveys for lymphatic filariasis (LF), schistosomiasis and soil-transmitted helminth (STH) infection have been recommended for this purpose. Integrated survey designs inevitably involve balancing the costs of(More)
The availability of large volumes of multimedia data presents many challenges to content retrieval. Sophisticated modern systems must efficiently process, index, and retrieve terabytes of mul-timedia data, determining what is relevant based on the user's query criteria and the system's domain specific knowledge. This paper reports our approach to(More)