The Video Tool Library (VTL) is one of the major normative components of the Reconfigurable Video Coding (RVC) standard. It specifies the set of functional units (FUs) that may be...
—In this paper, we introduce a local image descriptor, DAISY, which is very efficient to compute densely. We also present an EM-based algorithm to compute dense depth and occlusi...
Automatic image annotation is a promising way to achieve more effective image management and retrieval by using keywords. However, system performances of the existing state-of-the...
Here we describe a baseline-based binary shape coding method in which arbitrarily shaped object is represented by the traced 1-D data from baseline and turning point (TP). The sha...
Shi Hwa Lee, Dae-Sung Cho, Yu-Shin Cho, Sehoon Son...
Three-dimensional (3-D) models of outdoor scenes are widely used for object recognition, navigation, mixed reality, and so on. Because such models are often made manually with hig...