We present the first systematic study on concealed object detection (COD), which aims to
identify objects that are visually embedded in their background. The high intrinsic similarities …

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 …

RGB-D saliency detection has attracted increasing attention, due to its effectiveness and the
fact that depth cues can now be conveniently captured. Existing works often focus on …

Visual salient object detection (SOD) aims at finding the salient object (s) that attract human
attention, while camouflaged object detection (COD) on the contrary intends to discover the …

Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as
independent information and design separate networks for feature extraction from each …

Abstract Camouflaged Object Detection (COD) aims to detect objects with similar patterns
(eg, texture, intensity, colour, etc) to their surroundings, and recently has attracted growing …

RGB-D salient object detection (SOD) recently has attracted increasing research interest
and many deep learning methods based on encoder-decoder architectures have emerged …

Vision transformer networks have shown superiority in many computer vision tasks. In this
paper, we take a step further by proposing a novel generative vision transformer with latent …

RGB-D salient object detection (SOD) recently has attracted increasing research interest by
benefiting conventional RGB SOD with extra depth information. However, existing RGB-D …

RGB-D saliency detection aims to fuse multi-modal cues to accurately localize salient
regions. Existing works often adopt attention modules for feature modeling, with few …