Latent Layout Analysis (LLA) is a novel unsupervised learning technique to discover objects in unseen images using a set of un-annotated training images. LLA defines a generative ...
In this paper, we present the current development progress of our dynamic insert strategy based on the Intelligent Cluster Index (ICIx), which is a new type of multidimensional da...
The chapter describes visual classification by a hierarchy of semantic fragments. In fragment-based classification, objects within a class are represented by common sub-structures ...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
In this paper, we present a novel approach to learning semantic localized patterns with binary projections in a supervised manner. The pursuit of these binary projections is refor...