This paper describes a GPU framework for the real-time visualization of natural textured terrains, as well as the steps that are needed to populate them on-the-fly with tens of tho...
In this paper, we propose a new semantic event detection algorithm in structured video. A hybrid method that combines HMM with SVM to detect semantic events in video is proposed. T...
Tae Meon Bae, Cheon Seog Kim, Sung Ho Jin, Ki Hyun...
We present an approach for the supervised online learning of object representations based on a biologically motivated architecture of visual processing. We use the output of a rece...
Usually, in traditional text categorization systems based on Vector Space Model, there is no context information in a feature vector, which limited the performance of the system. T...
The work proposes a hierarchical architecture for learning amic scenes at various levels of knowledge abstraction. The raw visual information is processed at different stages to g...