Pseudo-likelihood and contrastive divergence are two well-known examples of contrastive methods. These algorithms trade off the probability of the correct label with the probabili...
In this paper, we develop a heuristic, progression based conformant planner, called CNF, which represents belief states by a special type of CNF formulae, called CNF-states. We de...
This paper presents a method for movie genre categorization of movie trailers, based on scene categorization. We view our approach as a step forward from using only low-level visu...
Howard Zhou, Tucker Hermans, Asmita V. Karandikar,...
In this paper, we consider the problem of speaker verification as a two-class object detection problem in computer vision, where the object instances are 1-D short-time spectral v...
Algorithms such as Least Median of Squares (LMedS) and Random Sample Consensus (RANSAC) have been very successful for low-dimensional robust regression problems. However, the comb...