In this paper, we propose a generative model for representing complex motion, such as wavy river, dancing fire and dangling cloth. Our generative method consists of four component...
Unsupervised learning of linguistic structure is a difficult problem. A common approach is to define a generative model and maximize the probability of the hidden structure give...
In this paper, we describe our work-in-progress with collaborative understanding of distributed ontologies in a multiagent framework. As reported earlier, the objective of this fr...
We propose an online algorithm based on local sparse representation for robust object tracking. Local image patches of a target object are represented by their sparse codes with a...
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...