Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

Salient object detection, which simulates human visual perception in locating the most
significant object (s) in a scene, has been widely applied to various computer vision tasks …

Vision transformers have recently shown strong global context modeling capabilities in
camouflaged object detection. However, they suffer from two major limitations: less effective …

The recently proposed camouflaged object detection (COD) attempts to segment objects that
are visually blended into their surroundings, which is extremely complex and difficult in real …

Most recent methods for RGB (red–green–blue)-thermal salient object detection (SOD)
involve several floating-point operations and have numerous parameters, resulting in slow …

Camouflaged object detection (COD), segmenting objects that are elegantly blended into
their surroundings, is a valuable yet challenging task. Existing deep-learning methods often …

Existing state-of-the-art saliency detection methods heavily rely on CNN-based
architectures. Alternatively, we rethink this task from a convolution-free sequence-to …

A main challenge faced in the deep learning-based Underwater Image Enhancement (UIE)
is that the ground truth high-quality image is unavailable. Most of the existing methods first …

Focusing on the issue of how to effectively capture and utilize cross-modality information in
RGB-D salient object detection (SOD) task, we present a convolutional neural network …

Convolutional neural networks (CNNs) are good at extracting contexture features within
certain receptive fields, while transformers can model the global long-range dependency …