We present an architecture for the online learning of object representations based on a visual cortex hierarchy developed earlier. We use the output of a topographical feature hier...
In order to summarize a video consisting of a sequence of different activities, there are three fundamental problems: tracking the objects of interest, detecting the activity chan...
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
Abstract. In this paper, we develop a content-based video classification approach to support semantic categorization, high-dimensional indexing and multi-level access. Our contribu...
Tracking and recognizing non-rigid objects in video image sequences are complex tasks of increasing importance to many applications. In this paper, we present a hierarchical reali...
SangKyu Kang, Joon Ki Paik, Besma R. Abidi, Yan Zh...