We propose a sequential Monte Carlo data association algorithm based on a two-level computational framework for tracking varying number of interacting objects in dynamic scene. Fi...
We propose a local, generative model for similarity-based classification. The method is applicable to the case that only pairwise similarities between samples are available. The c...
Graph-based methods for semi-supervised learning have recently been shown to be promising for combining labeled and unlabeled data in classification problems. However, inference f...
This paper presents a syntax-driven approach to question answering, specifically the answer-sentence selection problem for short-answer questions. Rather than using syntactic fea...
We propose novel approaches for optimizing the detection performance in spoken language recognition. Two objective functions are designed to directly relate model parameters to tw...