We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natur...
We need to harness the growing wealth of information in digital libraries to support intellectual work involving creative and exploratory processes. Prior research on hypertext au...
We propose a hybrid body representation that represents each typical pose by both template-like view information and part-based structural information. Specifically, each body par...
Spatial priors play crucial roles in many high-level vision tasks, e.g. scene understanding. Usually, learning spatial priors relies on training a structured output model. In this...
Extensive labeled data for image annotation systems, which learn to assign class labels to image regions, is difficult to obtain. We explore a hybrid model framework for utilizing...