Structured outputs such as multidimensional vectors or graphs are frequently encountered in real world pattern recognition applications such as computer vision, natural language pr...
In this paper, a novel method to learn the intrinsic object structure for robust visual tracking is proposed. The basic assumption is that the parameterized object state lies on a...
Inter- and intra-observer variability exists in any measurements made on medical images. There are two sources of variability. The first occurs when the observers identify and loc...
Mehul P. Sampat, Zhou Wang, Mia K. Markey, Gary J....
The performance of a content based image retrieval (CBIR) system is inherently constrained by the features adopted to represent the images in the database. In this paper, a new ap...
Multi-task learning (MTL) aims to improve generalization performance by learning multiple related tasks simultaneously. In this paper, we consider the problem of learning shared s...