This paper addresses online learning of reference object distribution in the context of two hybrid tracking schemes that combine the mean shift with local point feature correspond...
Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been u...
Recently, in generic object recognition research, a classification technique based on integration of image features is garnering much attention. However, with a classifying techn...
This paper presents an object tracking method for object-based video processing which uses a two-dimensional (2-D) Gabor wavelet transform (GWT) and a 2-D golden section algorithm....
Feature selection, as a preprocessing step to machine learning, has been very effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and imp...