Despite the tremendous advances achieved over the past years by deep lea...
The increasing scale of alternating current and direct current (AC/DC) h...
We consider a new problem of few-shot learning of compact models.
Meta-l...
For a non-technical audience, new concepts from computer science and
eng...
We introduce Tuna, a static analysis approach to optimizing deep neural
...
Deep learning implementations on CPUs (Central Processing Units) are gai...
As a natural way for human-computer interaction, fixation provides a
pro...
Modern deep neural networks increasingly make use of features such as dy...
Most existing instance segmentation methods only focus on 2D objects and...
In recent years, person re-identification (PReID) has become a hot topic...
We trained Binarized Neural Networks (BNNs) on the high resolution Image...