Speech recognition (ASR) and speaker diarization (SD) models have
tradit...
There has been an ongoing cycle where stronger defenses against adversar...
Adversarial examples raise questions about whether neural network models...
Adversarial examples are inputs to machine learning models designed by a...
We propose the autofocus convolutional layer for semantic segmentation w...
Humans make complex inferences on faces, ranging from objective properti...
The Nonlinear autoregressive exogenous (NARX) model, which predicts the
...
Recent advances in deep learning, especially deep convolutional neural
n...
Are face and object recognition abilities independent? Although it is
co...
It is commonly believed that the central visual field is important for
r...
The human visual system has a hierarchical structure consisting of layer...