This study describes experiments on automatic detection of semantic concepts, which are textual descriptions about the digital video content. The concepts can be further used in c...
We present a new feature based algorithm for stereo correspondence. Most of the previous feature based methods match sparse features like edge pixels, producing only sparse dispar...
We present a new technique for extracting local features from images of architectural scenes, based on detecting and representing local symmetries. These new features are motivate...
In this paper we discuss a general framework for feature selection based on nonparametric statistics. The three stage approach we propose is based on the assumption that the avail...
The increasing availability of object-based video content requires new technologies for automatically extracting and matching of the low level features of arbitrarily shaped video...