A purely bottom-up model of visual attention is proposed and compared to five state-of-the-art models. The role of the low-level visual features is examined in two contexts. Two da...
Multi-frame motion estimation is a novel technique to improve the video coding efficiency. However, the computational complexity in motion search is usually a bottleneck in the vi...
We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Ne...
A robust VAR-based (vector autoregressive) model is introduced for motion prediction in 3D hand tracking. This dynamic VAR motion model is learned in an online manner. The kinemat...
This paper presents an enhanced genetic algorithm for the protein structure prediction problem. A new fitness function, that uses the concept of radius of gyration, is proposed. Al...