Visual grounding (VG) tasks involve explicit cross-modal alignment, as
s...
Stochastically Extended Adversarial (SEA) model is introduced by Sachs e...
Positioning with one inertial measurement unit and one ranging sensor is...
As the successor of H.265/HEVC, the new versatile video coding standard
...
A practical autonomous driving system urges the need to reliably and
acc...
This technical report presents the online and real-time 2D and 3D
multi-...
In this technical report, we introduce our winning solution "HorizonLiDA...
High-efficiency point cloud 3D object detection operated on embedded sys...
Deep Models, typically Deep neural networks, have millions of parameters...
The Localization of the target object for data retrieval is a key issue ...