The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...
Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiplescale mu...
Why does placing an object from one photograph into another often make the colors of that object suddenly look wrong? One possibility is that humans prefer distributions of colors...
Aggregating spatial objects is a necessary step in generating spatial data cubes to support roll-up/drill-down operations. Current approaches face performance bottleneck issues wh...
Machine Learning can be divided into two schools of thought: generative model learning and discriminative model learning. While the MCS community has been focused mainly on the lat...