We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
Constrained random simulation is the main workhorse in today’s hardware verification flows. It requires the random generation of input stimuli that obey a set of declaratively...
Various timing-based mutualexclusion algorithms have been proposed that guarantee mutual exclusion if certain timing assumptions hold. In this paper, we examine how these algorith...
We present a randomized DNA algorithm for k-SAT based on the classical algorithm of Paturi et al. [8]. For an n-variable, m-clause instance of k-SAT (m > n), our algorithm finds...