While lightweight ViT framework has made tremendous progress in image super-resolution,
its uni-dimensional self-attention modeling, as well as homogeneous aggregation scheme …

Vision Transformers (ViTs) have achieved impressive performance over various computer
vision tasks. However, modeling global correlations with multi-head self-attention (MSA) …

In recent years, the deep learning-based hyperspectral image (HSI) classification method
has achieved great success, and the convolutional neural network (CNN) method has …

In a typical image inpainting task, the location and shape of the damaged or masked area is
often random and irregular. The vanilla convolutions widely used in learning-based …

Depth map super-resolution (DSR) has been a fundamental task for 3D computer vision.
While arbitrary scale DSR is a more realistic setting in this scenario, previous approaches …

Depth map super-resolution (DSR) plays an indispensable role in 3D vision. We discover an
non-trivial spectral phe-nomenon: the components of high-resolution (HR) and low …

Convolutional Neural Network (CNN), with its remarkable feature extraction capabilities, has
proven to perform superior in computer vision applications. Conversely, transformer-based …

Dynamic convolution has achieved significant gain in performance and computational
complexity, thanks to its powerful representation capability given limited filter number/layers …

Medical image segmentation is pivotal in disease diagnosis and treatment. This paper
presents a novel network architecture for medical image segmentation, termed TransDLNet …

Pine nuts, as a highly nutritious and medicinally valuable food, are susceptible to various
defects during their cultivation, harvesting, and transportation, which can reduce their …