Spatio-temporal interest region detectors can be used in the analysis of video to determine sparse, informative regions as candidates for feature extraction. In this paper we comp...
We introduce the Multiple Relationship Similarity Spreading Algorithm (MRSSA) to enhance IR effectiveness. This method has similarity computed in an iterative “spreading” fash...
Abstract. We propose a new unsupervised training method for acquiring probability models that accurately segment Chinese character sequences into words. By constructing a core lexi...
This paper describes experiments documenting significant variations in word usage patterns within social subgroups of AI researchers. As some phrases have very different collocati...
— We present a probabilistic framework for visual correspondence, inertial measurements and Egomotion. First, we describe a simple method based on Gabor filters to produce corre...