The detection and tracking of three-dimensional human body models has progressed rapidly but successful approaches typically rely on accurate foreground silhouettes obtained using...
We present a novel model for human action categorization. A video sequence is represented as a collection of spatial and spatial-temporal features by extracting static and dynamic...
We develop a generic method for the review matching problem, which is to match unstructured text reviews to a list of objects, where each object has a set of attributes. To this e...
Nilesh N. Dalvi, Ravi Kumar, Bo Pang, Andrew Tomki...
Generative models of pattern individuality attempt to represent the distribution of observed quantitative features, e.g., by learning parameters from a database, and then use such...
—Automatic understanding of human behavior is an important and challenging objective in several surveillance applications. One of the main problems of this task consists in accur...