This paper presents a framework for directly addressing issues arising from self-occlusions and ambiguities due to the lack of depth information in vector-based representations. V...
Abstract. Even a relatively unstructured captioned image set depicting a variety of objects in cluttered scenes contains strong correlations between caption words and repeated visu...
This paper presents a method to quantitatively evaluate
information contributions of individual bottom-up and topdown
computing processes in object recognition. Our objective
is...
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
Many real-world domains exhibit rich relational structure and stochasticity and motivate the development of models that combine predicate logic with probabilities. These models de...
Sriraam Natarajan, Prasad Tadepalli, Eric Altendor...