Jointly estimating the optical flow and depth tasks in real-world scenes presents considerable hurdles due to some phenomena, such as occlusion, ambiguous textures, and illumination variation. The lack of guidance from the labeled data makes these challenges harder to overcome. This paper presents a novel approach to learning the regions with high uncertainties in a self-supervised manner. Our met...Show More
To decarbonize space heating systems, energy efficiency improvement plays the same important role as adopting emerging clean energy technologies. Traditional space heating control systems are often developed under the assumption of uniform temperature distribution within a bounded space without considering large thermal inertias, which leads to much delayed control actions. This paper presents a h...Show More
