Current orthogonal matching pursuit (OMP) algorithms calculate the correlation between two vectors using the inner product operation and minimize the […]
We propose to learn a fully-convolutional network model that consists of a Chain of Identity Mapping Modules and residual on […]
Classification of HEp-2 cell patterns plays a significant role in the indirect immunofluorescence test for identifying autoimmune diseases in the […]
High-frequency regions like edges compromise the image denoising performance. In traditional hand-crafted systems, image edges/textures were regularly used to restore […]
Yesterday, the SCOPE program from Network10 aired an episode on our sustainable fishing project WANDA®, a software which uses advanced […]
Depth completion recovers dense depth from sparse measurements, e.g., LiDAR. Existing depth-only methods use sparse depth as the only input. […]
Overview Artificial intelligence is impacting the world in many ways. The capability of machine learning algorithms for AI profoundly relies upon the data. […]
Water on road is a potential hazard for road vehicles. In complex traffic, it is difficult for drivers to safely […]
Effectively describing and recognizing leaf shapes under arbitrary variations, particularly from a large database, remains an unsolved problem. In this […]
Saliency detection is important in computer vision. However, most of the existing saliency models are designed for visible images. It […]
