Interpolated images have data redundancy, and special correlation exists among neighboring pixels, which is a crucial clue in digital forensics. We design a neural network based f...
Lattice-based approaches have been widely used in spoken document retrieval to handle the speech recognition uncertainty and errors. Position Specific Posterior Lattices (PSPL) an...
Abstract—We present an extension of automatic image annotation that takes the context of a picture into account. Our core assumption is that users do not only provide individual ...
We present a discriminative method for learning selectional preferences from unlabeled text. Positive examples are taken from observed predicate-argument pairs, while negatives ar...
We present our experience in applying a rule induction technique to an extremely imbalanced pharmaceutical data set. We focus on using a variety of performance measures to evaluate...