Shapelets and CNN are two typical approaches to model time series. Shapelets aim at finding a set of sub-sequences that extract feature-based interpretable shapes, but may suffer from accuracy and ...

Abstract: We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large ...

Abstract: State-of-the-art lane detection methods often rely on specific knowledge about lanes – such as straight lines and parametric curves – to detect lane lines. While the specific knowledge can ...

Spyder needs a true standalone version. The current standalone installation still requires spyder-kernels, which has enough dependencies to cause serious conflicts for an environment. There is also ...