The task of Visual Object Navigation (VON) involves an agent's ability t...
Despite recent advances in video-based action recognition and robust
spa...
Visual-audio navigation (VAN) is attracting more and more attention from...
We study building a multi-task agent in Minecraft. Without human
demonst...
In dense neighborhoods, there are often dozens of homes in close proximi...
Imagine a map of your home with all of your connected devices (computers...
While using a speaker verification (SV) based system in a commercial
app...
A large amount of wastewater has been produced nowadays. Wastewater trea...
Classification is a pivotal function for many computer vision tasks such...
We propose a semi-supervised learning approach for video classification,...
This paper proposes a novel approach for crowd counting in low to high
d...
We address the recognition of agent-in-place actions, which are associat...
This paper addresses the problem of detecting relevant motion caused by
...