A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
How to incorporate cross-modal complementarity sufficiently is the cornerstone question for RGB-D salient object detection. ...
The experiments on public datasets show the effectiveness of the proposed CA-Fuse module and the RGB-D salient object detection network. ...
Figure 2 : 2 The architecture of the proposed progressively complementarity-aware fusion network for RGB-D salient object detection. ...
doi:10.1109/cvpr.2018.00322
dblp:conf/cvpr/ChenL18
fatcat:4wmrj7e43vdb3irinfkilca63q
Dynamic Message Propagation Network for RGB-D Salient Object Detection
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This paper presents a novel deep neural network framework for RGB-D salient object detection by controlling the message passing between the RGB images and depth maps on the feature level and exploring ...
Compared with 17 state-of-the-art methods on six benchmark datasets for RGB-D salient object detection, experimental results show that our method outperforms all the others, both quantitatively and visually ...
Abstract-This paper presents a novel deep neural network framework for RGB-D salient object detection by controlling the message passing between the RGB images and depth maps on the feature level and exploring ...
arXiv:2206.09552v1
fatcat:rzcne743q5ewvedczwzkzkilo4
Depth-aware Glass Surface Detection with Cross-modal Context Mining
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In addition, we propose a large-scale RGB-D glass surface detection dataset, called RGB-D GSD, for RGB-D glass surface detection. ...
In this paper, we propose a novel framework for glass surface detection by incorporating RGB-D information, with two novel modules: (1) a cross-modal context mining (CCM) module to adaptively learn individual ...
] are adopted in recent works for salient object detection. ...
arXiv:2206.11250v1
fatcat:poh5gc4d7rfwxnpkzv24v5tm6u
CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The goal of this work is to present a systematic solution for RGB-D salient object detection, which addresses the following three aspects with a unified framework: modal-specific representation learning ...
Furthermore, a top-down fusion structure is constructed for sufficient cross-modal interactions and cross-level transmissions. ...
RGB-D salient object detection. ...
arXiv:1909.09309v1
fatcat:qdg64qx6kjbpxbjpmwlzjrqhcm
Is Depth Really Necessary for Salient Object Detection?
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Salient object detection (SOD) is a crucial and preliminary task for many computer vision applications, which have made progress with deep CNNs. ...
Taking the advantages of RGB and RGBD methods, we propose a novel depth-aware salient object detection framework, which has following superior designs: 1) It only takes the depth information as training ...
Figure 1 : 1 Motivation of our depth-aware salient object detection. b): captured depth groundtruth. c): predicted depth awareness by DASNet. d): depth-aware error weights for salient correction. e) and ...
arXiv:2006.00269v2
fatcat:vvodrtnphrhm7agdepe7ryktwi
RGB-D salient object detection: A survey
2021
Computational Visual Media
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Finally, we discuss several challenges and open directions of RGB-D based salient object detection for future research. ...
Moreover, to investigate the ability of existing models to detect salient objects, we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection ...
Acknowledgements This research was supported by a Major Project for a New Generation of AI under Grant No. 2018AAA0100400, National Natural Science Foundation of China (61922046), and Tianjin Natural Science ...
doi:10.1007/s41095-020-0199-z
pmid:33432275
pmcid:PMC7788385
fatcat:foiz2zth4vckjfuhvh524hwdtq
Select, Supplement and Focus for RGB-D Saliency Detection
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
However, RGB-D saliency detection methods are also negatively influenced by randomly distributed erroneous or missing regions on the depth map or along the object boundaries. ...
In this paper, we propose a new framework for accurate RGB-D saliency detection taking account of global location and local detail complementarities from two modalities. ...
Innovation Foundation of Dalian (2019J12GX034), the National Natural Science Foundation of China (61976035, 61725202, U1903215, U1708263, 61829102, 91538201 and 61751212), and the Fundamental Research Funds for ...
doi:10.1109/cvpr42600.2020.00353
dblp:conf/cvpr/ZhangRPRL20
fatcat:4n3x4eeoenglva2fsbn3dmjhgy
cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Fusing complementary information of RGB and depth has been demonstrated to be effective for image salient object detection which is known as RGB-D salient object detection problem. ...
for RGB-D saliency detection problem. ...
We develop a novel cross-modality Saliency Generative Adversarial Network (cmSalGAN) for RGB-D salient object detection. ...
arXiv:1912.10280v2
fatcat:zaxsm6o6mfbv5oslfg5wjwxywy
Multi-modal Weights Sharing and Hierarchical Feature Fusion for RGBD Salient Object Detection
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Salient object detection (SOD) aims to identify and locate the most attractive regions in an image, which has been widely used in various vision tasks. ...
First, we propose a CNN-based cross-modal transfer learning, which learn knowledge from sufficient labeled RGB salient object datasets and guide the depth domain feature extraction. ...
[21] designed a priormodel guided depth-enhanced network (PDNet) for salient object detection. ...
doi:10.1109/access.2020.2971509
fatcat:aze3ddzokjcy3pn764iffcibsm
Generative Transformer for Accurate and Reliable Salient Object Detection
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we conduct extensive research on exploiting the contributions of transformers for accurate and reliable salient object detection. ...
We apply our proposed iGAN to both fully and weakly supervised salient object detection, and explain that iGAN within the transformer framework leads to both accurate and reliable salient object detection ...
and testing datasets for RGB-D salient object detection. ...
arXiv:2104.10127v5
fatcat:3lamfyvkifex7lkclw2tm337dq
Position-Aware Relation Learning for RGB-Thermal Salient Object Detection
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To address this problem,we propose a position-aware relation learning network (PRLNet) for RGB-T SOD based on swin transformer. ...
RGB-Thermal salient object detection (SOD) combines two spectra to segment visually conspicuous regions in images. Most existing methods use boundary maps to learn the sharp boundary. ...
RGB-T Salient Object Detection Compared to RGB images, RGB-T images offer more information of salient objects [40] . ...
arXiv:2209.10158v1
fatcat:y3otqk2l5bbdhdcccmjapx7wgu
Interactive Context-Aware Network for RGB-T Salient Object Detection
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Salient object detection (SOD) focuses on distinguishing the most conspicuous objects in the scene. However, most related works are based on RGB images, which lose massive useful information. ...
In this paper, we propose a novel network called Interactive Context-Aware Network (ICANet). It contains three modules that can effectively perform the cross-modal and cross-scale fusions. ...
RGB-D Salient Object Detection RGB-D SOD is a typical multi-modal SOD task, in which D means depth information. Multiple deep learning methods have been proposed in recent years. Chen et al. ...
arXiv:2211.06097v1
fatcat:lplxbndxx5bq7kp57xmx4v4r4q
Multi-scale iterative refinement network for RGB-D salient object detection
2021
Engineering applications of artificial intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2201.09574v1 fatcat:hvh6cmdwvvbuxf6s7bpfod6cte
The extensive research leveraging RGB-D information has been exploited in salient object detection. ...
Cross-modal fusion and multi-scale refinement are still an open problem in RGB-D salient object detection task. ...
RGB-D Salient Object Detection RGB-D salient object detection can be roughly classified into early fusion, middle fusion and late fusion. ...
doi:10.1016/j.engappai.2021.104473
fatcat:2dj6azts2fajlju7c55mnpw5sq
Adaptive Fusion for RGB-D Salient Object Detection
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
RGB-D salient object detection aims to identify the most visually distinctive objects in a pair of color and depth images. ...
Specifically, we design a two-streamed convolutional neural network (CNN), each of which extracts features and predicts a saliency map from either RGB or depth modality. ...
Switch map is the map learned in our network for adaptive fusion.
Fig. 2 : 2 The overview of our framework for RGB-D salient object detection. ...
arXiv:1901.01369v2
fatcat:y4kj2aonovgmrdiqqlbcwdpm3u
Adaptive Fusion for RGB-D Salient Object Detection
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
INDEX TERMS RGB-D salient object detection, switch map, edge-preserving. ...
RGB-D (red, green, blue, and depth) salient object detection aims to identify the most visually distinctive objects in a pair of color and depth images. ...
The overview of our framework for RGB-D salient object detection. ...
doi:10.1109/access.2019.2913107
fatcat:xr2foirygjezxh6b2vzmiv6ney
« Previous
Showing results 1 — 15 out of 1,957 results