Communication latencies within critical sections constitute a major bottleneck in some classes of emerging parallel workloads. In this paper, we argue for the use of Inferentially...
In supervised learning, a training set consisting of labeled instances is used by a learning algorithm for generating a model (classifier) that is subsequently employed for decidi...
When an image is viewed at varying resolutions, it is known to create discrete perceptual jumps or transitions amid the continuous intensity changes. In this paper, we study a per...
Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D pose. Learning such multi-modal models ...
Lifting can greatly reduce the cost of inference on firstorder probabilistic graphical models, but constructing the lifted network can itself be quite costly. In online applicatio...