The global demand for food and bioenergy changes associated with land use and land
cover change (LULCC) has raised concerns about the environment, global warming, and …

Autonomous vehicles are becoming central for the future of mobility, supported by advances
in deep learning techniques. The performance of aself-driving system is highly dependent …

Self-supervised learning methods have witnessed a recent surge of interest after proving
successful in multiple application fields. In this work, we leverage these techniques, and we …

Multimodal classification research has been gaining popularity with new datasets in
domains such as satellite imagery, biometrics, and medicine. Prior research has shown the …

Point cloud is a widely used 3D data form, which can be produced by depth sensors, such
as Light Detection and Ranging (LIDAR) and RGB-D cameras. Being unordered and …

3D semantic segmentation is a fundamental task for robotic and autonomous driving
applications. Recent works have been focused on using deep learning techniques, whereas …

As an important application in remote sensing, landcover classification remains one of the
most challenging tasks in very-high-resolution (VHR) image analysis. As the rapidly …

Automated semantic segmentation and object detection are of great importance in
geospatial data analysis. However, supervised machine learning systems such as …

Automated construction progress monitoring is the prevalent domain amongst researchers,
with much potential for improving digital monitoring technologies and related processes …

The rapid advancement of remote sensing technology has significantly enhanced the
temporal resolution of remote sensing data. Multitemporal remote sensing image …