We present a method for figure-ground segregation of moving objects from monocular video sequences. The approach is based on tracking extracted contour fragments, in contrast to ...
The algorithm presented in this paper aims to segment the foreground objects in video (e.g., people) given timevarying, textured backgrounds. Examples of time-varying backgrounds ...
In this paper we describe an approach that uses a combination of visual and audio features to cluster shots belonging to the same person together in video programs. We use color h...
—An open vision problem is to automatically track the articulations of people from a video sequence. This problem is difficult because one needs to determine both the number of p...
In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlatio...