Abstract: Hyperspectral anomaly detection (HAD) aims at effectively separating the anomaly target from the background. The low-rank and sparse matrix decomposition (LRaSMD) technique has shown great ...

Abstract: Digital Signal Processors (DSPs) rely on VLIW and SIMD architectures to provide significant advantages in real-time, low-power computation. The efficient implementation of matrix LU ...

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their ...