Data Warehouses and On-Line Analytical Processing systems rely on a multidimensional model that includes dimensions, hierarchies, and measures. Such model allows to express users&...
We propose an unsupervised, probabilistic method for learning visual feature hierarchies. Starting from local, low-level features computed at interest point locations, the method c...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...