We present a top-down statistical modeling approach to explore the semantic structure in the American football video. First, a semantic space is defined where the video semantic ...
Scalability and extended lifetime are two critical design goals of any large scale wireless sensor network. A two-tiered network model has been proposed recently for this purpose....
Many structured information extraction tasks employ collective graphical models that capture interinstance associativity by coupling them with various clique potentials. We propos...
Many computer vision algorithms include a robust estimation step where model parameters are computed from a data set containing a significant proportion of outliers. The RANSAC al...
This paper investigates the problem of designing decentralized representations to support monitoring and inferences in sensor networks. State-space models of physical phenomena su...
Juan Liu, Maurice Chu, Jie Liu, Jim Reich, Feng Zh...