Concealed object detection

DP Fan, GP Ji, MM Cheng… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
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 …

CIR-Net: Cross-modality interaction and refinement for RGB-D salient object detection

R Cong, Q Lin, C Zhang, C Li, X Cao… - … on Image Processing, 2022 - ieeexplore.ieee.org
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 …

Specificity-preserving RGB-D saliency detection

T Zhou, H Fu, G Chen, Y Zhou… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

Uncertainty-aware joint salient object and camouflaged object detection

A Li, J Zhang, Y Lv, B Liu, T Zhang… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

Siamese network for RGB-D salient object detection and beyond

K Fu, DP Fan, GP Ji, Q Zhao, J Shen… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
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 …

Fast camouflaged object detection via edge-based reversible re-calibration network

GP Ji, L Zhu, M Zhuge, K Fu - Pattern Recognition, 2022 - Elsevier
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 via 3D convolutional neural networks

Q Chen, Z Liu, Y Zhang, K Fu, Q Zhao… - Proceedings of the AAAI …, 2021 - ojs.aaai.org
RGB-D salient object detection (SOD) recently has attracted increasing research interest
and many deep learning methods based on encoder-decoder architectures have emerged …

Learning generative vision transformer with energy-based latent space for saliency prediction

J Zhang, J Xie, N Barnes, P Li - Advances in Neural …, 2021 - proceedings.neurips.cc
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 …

Depth quality-inspired feature manipulation for efficient RGB-D salient object detection

W Zhang, GP Ji, Z Wang, K Fu, Q Zhao - Proceedings of the 29th ACM …, 2021 - dl.acm.org
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 …

Hidanet: Rgb-d salient object detection via hierarchical depth awareness

Z Wu, G Allibert, F Meriaudeau, C Ma… - … on Image Processing, 2023 - ieeexplore.ieee.org
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 …