,
volume 32
,
issue 7
,
pages 4486-4497
SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection
Publication type: Journal Article
Publication date: 2022-07-01
scimago Q1
wos Q1
SJR: 1.858
CiteScore: 15.4
Impact factor: 11.1
ISSN: 10518215, 15582205
Electrical and Electronic Engineering
Media Technology
Abstract
Convolutional neural networks (CNNs) are good at extracting contexture features within certain receptive fields, while transformers can model the global long-range dependency features. By absorbing the advantage of transformer and the merit of CNN, Swin Transformer shows strong feature representation ability. Based on it, we propose a cross-modality fusion model,
SwinNet
, for RGB-D and RGB-T salient object detection. It is driven by Swin Transformer to extract the hierarchical features, boosted by attention mechanism to bridge the gap between two modalities, and guided by edge information to sharp the contour of salient object. To be specific, two-stream Swin Transformer encoder first extracts multi-modality features, and then spatial alignment and channel re-calibration module is presented to optimize intra-level cross-modality features. To clarify the fuzzy boundary, edge-guided decoder achieves inter-level cross-modality fusion under the guidance of edge features. The proposed model outperforms the state-of-the-art models on RGB-D and RGB-T datasets, showing that it provides more insight into the cross-modality complementarity task.
Found
Nothing found, try to update filter.
Found
Nothing found, try to update filter.
Top-30
Journals
|
5
10
15
20
25
30
35
|
|
|
IEEE Transactions on Circuits and Systems for Video Technology
33 publications, 11.74%
|
|
|
IEEE Transactions on Instrumentation and Measurement
12 publications, 4.27%
|
|
|
IEEE Transactions on Image Processing
12 publications, 4.27%
|
|
|
Engineering Applications of Artificial Intelligence
9 publications, 3.2%
|
|
|
Pattern Recognition
9 publications, 3.2%
|
|
|
Expert Systems with Applications
9 publications, 3.2%
|
|
|
IEEE Access
9 publications, 3.2%
|
|
|
IEEE Transactions on Geoscience and Remote Sensing
8 publications, 2.85%
|
|
|
Knowledge-Based Systems
7 publications, 2.49%
|
|
|
Neurocomputing
7 publications, 2.49%
|
|
|
IEEE Transactions on Multimedia
7 publications, 2.49%
|
|
|
Lecture Notes in Computer Science
7 publications, 2.49%
|
|
|
Neural Networks
6 publications, 2.14%
|
|
|
Digital Signal Processing: A Review Journal
6 publications, 2.14%
|
|
|
Image and Vision Computing
6 publications, 2.14%
|
|
|
Multimedia Tools and Applications
5 publications, 1.78%
|
|
|
Applied Sciences (Switzerland)
4 publications, 1.42%
|
|
|
IEEE Signal Processing Letters
4 publications, 1.42%
|
|
|
Information Fusion
4 publications, 1.42%
|
|
|
IEEE Sensors Journal
4 publications, 1.42%
|
|
|
Visual Computer
3 publications, 1.07%
|
|
|
Remote Sensing
3 publications, 1.07%
|
|
|
ACM Transactions on Multimedia Computing, Communications and Applications
3 publications, 1.07%
|
|
|
Journal of Electronic Imaging
3 publications, 1.07%
|
|
|
IEEE Transactions on Pattern Analysis and Machine Intelligence
3 publications, 1.07%
|
|
|
Electronics (Switzerland)
2 publications, 0.71%
|
|
|
Applied Optics
2 publications, 0.71%
|
|
|
Measurement: Journal of the International Measurement Confederation
2 publications, 0.71%
|
|
|
IET Computer Vision
2 publications, 0.71%
|
|
|
5
10
15
20
25
30
35
|
Publishers
|
20
40
60
80
100
120
140
|
|
|
Institute of Electrical and Electronics Engineers (IEEE)
121 publications, 43.06%
|
|
|
Elsevier
82 publications, 29.18%
|
|
|
Springer Nature
32 publications, 11.39%
|
|
|
MDPI
16 publications, 5.69%
|
|
|
Association for Computing Machinery (ACM)
6 publications, 2.14%
|
|
|
Institution of Engineering and Technology (IET)
3 publications, 1.07%
|
|
|
Taylor & Francis
3 publications, 1.07%
|
|
|
SPIE-Intl Soc Optical Eng
3 publications, 1.07%
|
|
|
Optica Publishing Group
2 publications, 0.71%
|
|
|
King Saud University
1 publication, 0.36%
|
|
|
World Scientific
1 publication, 0.36%
|
|
|
Institute of Electronics, Information and Communications Engineers (IEICE)
1 publication, 0.36%
|
|
|
American Institute of Mathematical Sciences (AIMS)
1 publication, 0.36%
|
|
|
Public Library of Science (PLoS)
1 publication, 0.36%
|
|
|
SAGE
1 publication, 0.36%
|
|
|
Acoustical Society of America (ASA)
1 publication, 0.36%
|
|
|
Frontiers Media S.A.
1 publication, 0.36%
|
|
|
20
40
60
80
100
120
140
|
- We do not take into account publications without a DOI.
- Statistics recalculated weekly.
Are you a researcher?
Create a profile to get free access to personal recommendations for colleagues and new articles.
Metrics
281
Total citations:
281
Citations from 2024:
193
(68.68%)
The most citing journal
Citations in journal:
33
Cite this
GOST |
RIS |
BibTex |
MLA
Cite this
GOST
Copy
Liu Z. et al. SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection // IEEE Transactions on Circuits and Systems for Video Technology. 2022. Vol. 32. No. 7. pp. 4486-4497.
GOST all authors (up to 50)
Copy
Liu Z., Tan Y., HE Q., Xiao Y. SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection // IEEE Transactions on Circuits and Systems for Video Technology. 2022. Vol. 32. No. 7. pp. 4486-4497.
Cite this
RIS
Copy
TY - JOUR
DO - 10.1109/tcsvt.2021.3127149
UR - https://doi.org/10.1109/tcsvt.2021.3127149
TI - SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection
T2 - IEEE Transactions on Circuits and Systems for Video Technology
AU - Liu, Zhengyi
AU - Tan, Yacheng
AU - HE, QIAN
AU - Xiao, Yun
PY - 2022
DA - 2022/07/01
PB - Institute of Electrical and Electronics Engineers (IEEE)
SP - 4486-4497
IS - 7
VL - 32
SN - 1051-8215
SN - 1558-2205
ER -
Cite this
BibTex (up to 50 authors)
Copy
@article{2022_Liu,
author = {Zhengyi Liu and Yacheng Tan and QIAN HE and Yun Xiao},
title = {SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2022},
volume = {32},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
month = {jul},
url = {https://doi.org/10.1109/tcsvt.2021.3127149},
number = {7},
pages = {4486--4497},
doi = {10.1109/tcsvt.2021.3127149}
}
Cite this
MLA
Copy
Liu, Zhengyi, et al. “SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection.” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 7, Jul. 2022, pp. 4486-4497. https://doi.org/10.1109/tcsvt.2021.3127149.