Through the incorporation of derived classes and associations in class diagrams, this paper proposes a method to improve the specification power of multiplicity for n-ary associat...
This paper presents a generative model based approach to man-made structure detection in 2D natural images. The proposed approach uses a causal multiscale random field suggested i...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...
In the paper we present a generalized discriminative multiple instance learning algorithm (GD-MIL) for multimedia semantic concept detection. It combines the capability of the MIL...
This paper proposes a method for detecting object classes that exhibit variable shape structure in heavily cluttered images. The term "variable shape structure" is used t...
Jingbin Wang, Vassilis Athitsos, Stan Sclaroff, Ma...