Abstract- The large majority of existing clustering algorithms are centered around the notion of a feature, that is, individual data items are represented by their intrinsic proper...
Today many kinds of postprocessing are used in digital TV receivers or multimedia terminals for video signals to enhance the picture quality. To achieve this the properties of hum...
We formulate the problem of scene summarization as selecting a set of images that efficiently represents the visual content of a given scene. The ideal summary presents the most i...
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images re...
Honglak Lee, Roger Grosse, Rajesh Ranganath, Andre...
We introduce an approach to visualize stationary 2D vector fields with global uncertainty obtained by considering the transport of local uncertainty in the flow. For this, we ex...