We present an irregular image pyramid which is derived from multi-scale analysis of segmented watershed regions. Our framework is based on the development of regions in the Gaussia...
This paper presents a method for learning 3D object templates from view labeled object images. The 3D template is defined in a joint appearance and geometry space, and is compose...
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based mo...
Important ecological phenomena are often observed indirectly. Consequently, probabilistic latent variable models provide an important tool, because they can include explicit model...
Rebecca A. Hutchinson, Li-Ping Liu, Thomas G. Diet...
Abstract. Prosody has been actively studied as an important knowledge source for speech recognition and understanding. In this paper, we are concerned with the question of exploiti...