This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
This paper considers the problem of automatic assessment of local coherence. We present a novel entity-based representation of discourse which is inspired by Centering Theory and ...
Online learned tracking is widely used for it’s adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of erro...
Modern networks are very complex. It is highly desirable to reduce management complexity in next generation network design. Researchers have been seeking inspiration in natural ob...
Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require ite...