Branch taken rate and transition rate have been proposed as metrics to characterize the branch predictability. However, these two metrics may misclassify branches with regular his...
Most dense stereo correspondence algorithms start by establishing discrete pixel matches and later refine these matches to sub-pixel precision. Traditional sub-pixel refinement me...
Bidirectional recurrent neural network(BRNN) is a noncausal generalization of recurrent neural network(RNN). It can not learn remote information efficiently due to the problem of ...
Modern embedded applications usually have real-time constraints and they are implemented using heterogeneous multiprocessor systems-on-chip. Dimensioning a system requires accurat...
Stefan Valentin Gheorghita, Sander Stuijk, Twan Ba...
GestureBar is a novel, approachable UI for learning gestural interactions that enables a walk-up-and-use experience which is in the same class as standard menu and toolbar interfa...
Andrew Bragdon, Robert C. Zeleznik, Brian Williams...