Single image super-resolution (SISR) deals with a fundamental problem of upsampling a
low-resolution (LR) image to its high-resolution (HR) version. Last few years have witnessed …

The transformer architectures, based on self-attention mechanism and convolution-free
design, recently found superior performance and booming applications in computer vision …

The Gaussian kernel and its derivatives have already been employed for Convolutional
Neural Networks in several previous works. Most of these papers proposed to compute …

Estimating human poses from a video is at the foundation of many visual intelligent systems.
Various convolutional neural networks have been proposed, achieving state‐of‐the‐art …

Convolutional neural networks excel in a number of computer vision tasks. One of their most
crucial architectural elements is the effective receptive field size, which has to be manually …

Due to their powerful representational ability, convolutional neural networks (CNN) have
achieved great success in image super-resolution (SR). In the trained SR models such as …

Dense prediction tasks typically employ encoder-decoder architectures, but the prevalent
convolutions in the decoder are not image-adaptive and can lead to boundary artifacts …

This paper explores extensions and restrictions of shallow convolutional neural networks
with fixed kernels trained with a limited number of training samples. We extend the work …

针对网络层级间特征融合不足并缺乏高频特征的精准定位和获取, 以及低光图像和多个正常曝光
图像之间的不确定映射问题, 提出一种迭代注意力归一化流(Iterative attention normalization …

Medical image classification is a critical task in the field of healthcare, as it enables the
accurate diagnosis and treatment of several diseases. Here, we propose a novel approach …