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...
A successful representation of objects in the literature is as a collection of patches, or parts, with a certain appearance and position. The relative locations of the different p...
We consider the problem of unsupervised classification of temporal sequences of facial expressions in video. This problem arises in the design of an adaptive visual agent, which m...
This paper describes an unsupervised learning technique for modeling human locomotion styles, such as distinct related activities (e.g. running and striding) or variations of the ...