Document images are often degraded by various stains, significantly impacting their
readability and hindering downstream applications such as document digitization and …

Machine learning algorithms have achieved remarkable success across various disciplines,
use cases and applications, under the prevailing assumption that training and test samples …

Shadow detection is crucial for accurate scene understanding in computer vision, yet it is
challenged by the diverse appearances of shadows caused by variations in illumination …

Underwater images often exhibit poor quality, distorted color balance and low contrast due
to the complex and intricate interplay of light, water, and objects. Despite the significant …

Social media is increasingly plagued by realistic fake images, making it hard to trust content.
Previous algorithms to detect these fakes often fail in new, real-world scenarios because …

Unsupervised video object segmentation (VOS), also known as video salient object
detection, aims to detect the most prominent object in a video at the pixel level. Recently, two …

Interactive segmentation aims to accurately segment target objects with minimal user
interactions. However, current methods often fail to accurately separate target objects from …

Accurate segmentation of lesion regions is crucial for clinical diagnosis and treatment across
various diseases. While deep convolutional networks have achieved satisfactory results in …

Generative Adversarial Networks (GANs) have emerged as a prominent research focus for
image editing tasks, leveraging the powerful image generation capabilities of the GAN …

Medical landmark detection is crucial in various medical imaging modalities and
procedures. Although deep learning-based methods have achieve promising performance …