The Graphics Processing Unit (GPU) plays a central part in how you use a computer, irrespective of whether you use it for hardcore gaming or just regular tasks. There are two common types of GPUs, ...

Event-based cameras are bio-inspired vision sensors that mimic the sparse and asynchronous activation of the animal retina, offering advantages such as low latency and low computational load in ...

This paper presents an analysis of properties of two hybrid discretisation methods for Gaussian derivatives, based on convolutions with either the normalised sampled Gaussian kernel or the integrated ...

Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and width (number of ...

self, conv1_get, size_p1, bp_num1, bp_num2, bp_num3, rate_w=0.2, rate_t=0.2 :param conv1_get: [a,c,d], size, number, step of convolution kernel :param size_p1: pooling size :param bp_num1: units ...

Abstract: In Digital Image Processing, the discrete linear convolution is used as a basis for linear filtering. In this paper, the multiplier operation involved in discrete linear convolution ...

Abstract: This paper discusses the use of symmetric convolution and the discrete sine and cosine transforms (DSTs and DCTs) for general digital signal processing. The operation of symmetric ...