Convolutional neural network-based approaches have achieved remarkable progress in
semantic segmentation. However, these approaches heavily rely on annotated data which …

Training deep networks for semantic segmentation requires large amounts of labeled
training data, which presents a major challenge in practice, as labeling segmentation masks …

We present an end-to-end joint training framework that explicitly models 6-DoF motion of
multiple dynamic objects, ego-motion, and depth in a monocular camera setup without …

Pre-training has become a standard paradigm in many computer vision tasks. However,
most of the methods are generally designed on the RGB image domain. Due to the …

The booming interest in adversarial attacks stems from a misalignment between human
vision and a deep neural network (DNN),\ie~ a human imperceptible perturbation fools the …

Volumetric deep learning approach towards stereo matching aggregates a cost volume
computed from input left and right images using 3D convolutions. Recent works showed that …

On-road behavior analysis is a crucial and challenging problem in the autonomous driving
vision-based area. Several endeavors have been proposed to deal with different related …

We introduce an end-to-end joint training framework that explicitly models 6-DoF motion of
multiple dynamic objects, ego-motion, and depth in a monocular camera setup without …

In most of computer vision applications, motion blur is regarded as an undesirable artifact.
However, it has been shown that motion blur in an image may have practical interests in …

We present an end-to-end joint training framework that explicitly models 6-DoF motion of
multiple dynamic objects, ego-motion and depth in a monocular camera setup without …