Learning shape placements by example

Supplementary Material for earning Shape Placements by Example

Shape Arrays allow propagating arrays of shapes that adapt the number of elements to the surrounding geometry with a single placement propagation. The choice between scaling or repeating shapes to fill the bounding box of a placement can be specified separately for the width and height dimensions. To implement shape arrays, we specify a minimum spacing between shapes and find the maximum number...

Shape and Animation by Example

Novel example-based shape learning for fast face alignment

In this paper, a novel Example-based Shape Learning (ESL) strategy has been proposed for facial feature alignment. The method is motivated by an intuitive and experimental observation that there exists an approximate linearity relationship between the image difference and the shape difference, that is, similar face images imply similar face shapes. Therefore, given a learning set of face images...

Learning Video Processing by Example

We present an algorithm that approximates the output of an arbitrary video processing algorithm based on a pair of input and output exemplars. Our algorithm relies on learning the mapping between the input and output exemplars to model the processing that has taken place. We approximate the processing by observing that pixel neighborhoods similar in appearance and motion to those in the exempla...

ACCELERATED LEARNING BY ACTIVE EXAMPLE SELECTIONByoung

Much previous work on training multilayer neural networks has attempted to speed up the back-propagation algorithm using more sophisticated weight modiica-tion rules, whereby all the given training examples are used in a random or predetermined sequence. In this paper we investigate an alternative approach in which the learning proceeds on an increasing number of selected training examples, sta...