In this work, we parallelize high-level features in deep networks to
sel...
Traffic light detection is a challenging problem in the context of
self-...
This paper introduces an audio-visual speech enhancement system that
lev...
We investigate cross-quality knowledge distillation (CQKD), a knowledge
...
Precisely locating and segmenting medical instruments in images of minim...
The localization of fruits is an essential first step in automated
agric...
Class-agnostic object proposal generation is an important first step in ...
It is often desired to train 6D pose estimation systems on synthetic dat...
The video captioning task is to describe the video contents with natural...
Precise segmentation of objects is an important problem in tasks like
cl...
3D scene models are useful in robotics for tasks such as path planning,
...
This paper addresses the task of estimating the 6 degrees of freedom pos...
We propose a novel approach for class-agnostic object proposal generatio...
Objects of different classes can be described using a limited number of
...
We present an attention based visual analysis framework to compute
grasp...
Rotation estimation of known rigid objects is important for robotic
appl...