There is limited understanding of the information captured by deep
spati...
Deep spatiotemporal models are used in a variety of computer vision task...
Existing weakly or semi-supervised semantic segmentation methods utilize...
In this paper, we present a strategy for training convolutional neural
n...
In this paper, we challenge the common assumption that collapsing the sp...
In contrast to fully connected networks, Convolutional Neural Networks (...
Contrasting the previous evidence that neurons in the later layers of a
...
In this paper, we present a strategy for training convolutional neural
n...
Driver inattention is a large problem on the roads around the world. The...