In this paper, we propose a framework for isolating text regions from natural scene images. The main algorithm has two functions: it generates text region candidates, and it veriï...
With the advent of high throughput technologies, feature selection has become increasingly important in a wide range of scientific disciplines. We propose a new feature selection ...
A novel scheme is proposed for achieving motion segmentation in low-frame rate videos, with application to temporal super resolution. Probabilistic generative models are commonly ...
We propose a representation of concurrent actions; rather than invent a new formalism, we model them within the standard situation calculus by introducing the notions of global ac...
We present a method to automatically extract spatio-temporal descriptions of moving objects from synchronized and calibrated multi-view sequences. The object is modeled by a time-...