In this paper, we tackle the problem of characterizing the aesthetic appeal of consumer videos and automatically classifying them into high or low aesthetic appeal. First, we condu...
We describe techniques to optimally select landmarks for performing mobile robot localization by matching terrain maps. The method is based upon a maximum-likelihood robot localiza...
— In a data-mining approach, a model for estimation of Aerosol Optical Depth (AOD) from satellite observations is learned using collocated satellite and groundbased observations....
This paper proposes a new approach for hot event detection and summarization of news videos. The approach is mainly based on two graph algorithms: optimal matching (OM) and normali...
In this paper, in order to reduce the explosive increase of the search space as the input dimension grows, we present a new representation method for the structure of fuzzy rules, ...