In this work, we propose to use attributes and parts for recognizing human actions in still images. We define action attributes as the verbs that describe the properties of human...
Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy La...
We present a multispectral photometric stereo method for capturing geometry of deforming surfaces. A novel photometric calibration technique allows calibration of scenes containin...
Despite decades of study, robust shadow detection remains difficult, especially within a single color image. We describe a new approach to detect shadow boundaries in images of o...
Xiang Huang, Gang Hua, Jack Tumblin, Lance William...
Many algorithms for performing inference in graphical models have complexity that is exponential in the treewidth - a parameter of the underlying graph structure. Computing the (m...
In this paper, we consider the problem of unsupervised morphological analysis from a new angle. Past work has endeavored to design unsupervised learning methods which explicitly o...