With the explosion in the number of digital images taken every day, the demand for more
accurate and visually pleasing images is increasing. However, the images captured by …

Over the past two decades, medical imaging and diagnostic techniques have gained
immense attraction due to the rapid development in computing, internet, data storage and …

Diffusion-based image super-resolution (SR) methods are mainly limited by the low
inference speed due to the requirements of hundreds or even thousands of sampling steps …

Multi-view clustering, which exploits the multi-view information to partition data into their
clusters, has attracted intense attention. However, most existing methods directly learn a …

Recently, low-rank representation (LRR) methods have been widely applied for
hyperspectral anomaly detection, due to their potentials in separating the backgrounds and …

The discriminative model learning for image denoising has been recently attracting
considerable attentions due to its favorable denoising performance. In this paper, we take …

Excellent performance, real time and strong robustness are three vital requirements for
infrared small target detection. Unfortunately, many current state-of-the-art methods merely …

Infrared small target detection plays an important role in precision guidance, infrared
warning, and other applications. The infrared patch-tensor (IPT) model has good detection …

Hyperspectral image (HSI) and multispectral image (MSI) fusion, which fuses a low-spatial-
resolution HSI (LR-HSI) with a higher resolution multispectral image (MSI), has become a …

In this paper, we analyze two popular network compression techniques, ie filter pruning and
low-rank decomposition, in a unified sense. By simply changing the way the sparsity …