The ranking function used by search engines to order results is learned from labeled training data. Each training point is a (query, URL) pair that is labeled by a human judge who...
Rakesh Agrawal, Alan Halverson, Krishnaram Kenthap...
Many common materials, including fruit, wax and human skin, are somewhat translucent. What makes an object look translucent or opaque? Here we use a recently developed computer gr...
Roland W. Fleming, Henrik Wann Jensen, Heinrich H....
In the real visual world, the number of categories a classifier needs to discriminate is on the order of hundreds or thousands. For example, the SUN dataset [24] contains 899 sce...
Sets of named entities are used heavily at commercial search engines such as Google, Yahoo and Bing. Acquiring sets of entities typically consists of combining semi-supervised exp...
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...