Hidanet: Rgb-d salient object detection via hierarchical depth awareness
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 …
regions. Existing works often adopt attention modules for feature modeling, with few …
CATNet: A cascaded and aggregated transformer network for RGB-D salient object detection
F Sun, P Ren, B Yin, F Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Salient object detection (SOD) is an important preprocessing operation for various computer
vision tasks. Most of existing RGB-D SOD models employ additive or connected strategies to …
vision tasks. Most of existing RGB-D SOD models employ additive or connected strategies to …
VP-Net: Voxels as points for 3-D object detection
The 3-D object detection with light detection and ranging (LiDAR) point clouds is a
challenging problem, which requires 3-D scene understanding, yet this task is critical to …
challenging problem, which requires 3-D scene understanding, yet this task is critical to …
Point-aware interaction and cnn-induced refinement network for RGB-D salient object detection
By integrating complementary information from RGB image and depth map, the ability of
salient object detection (SOD) for complex and challenging scenes can be improved. In …
salient object detection (SOD) for complex and challenging scenes can be improved. In …
Dformer: Rethinking rgbd representation learning for semantic segmentation
We present DFormer, a novel RGB-D pretraining framework to learn transferable
representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) …
representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) …
UTLNet: Uncertainty-aware transformer localization network for RGB-depth mirror segmentation
Mirror segmentation, an emerging discipline in the field of computer vision, involves the
identification and marking of mirrors in an image. Current mirror segmentation methods rely …
identification and marking of mirrors in an image. Current mirror segmentation methods rely …
Modal evaluation network via knowledge distillation for no-service rail surface defect detection
Deep learning techniques have largely solved the problem of rail surface defect detection
(SDD), however, two aspects have yet to be addressed. In most existing approaches, two …
(SDD), however, two aspects have yet to be addressed. In most existing approaches, two …
Mffnet: Multi-modal feature fusion network for vdt salient object detection
This article discusses the limitations of single-and two-modal salient object detection (SOD)
methods and the emergence of multi-modal SOD techniques that integrate Visible, Depth, or …
methods and the emergence of multi-modal SOD techniques that integrate Visible, Depth, or …
: Edge-Aware Multimodal Transformer for RGB-D Salient Object Detection
G Chen, Q Wang, B Dong, R Ma, N Liu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
RGB-D salient object detection (SOD) has gained tremendous attention in recent years. In
particular, transformer has been employed and shown great potential. However, existing …
particular, transformer has been employed and shown great potential. However, existing …
TMNet: Triple-modal interaction encoder and multi-scale fusion decoder network for VDT salient object detection
Salient object detection methods based on two-modal images have achieved remarkable
success with the aid of image acquisition equipment. However, environmental factors often …
success with the aid of image acquisition equipment. However, environmental factors often …