,
volume 43
,
issue 10
,
pages 3349-3364
Deep High-Resolution Representation Learning for Visual Recognition
Jing-Dong Wang
1
,
Ke Sun
2
,
Tianheng Cheng
3
,
Borui Jiang
4
,
Chaorui Deng
5
,
Zhao Yang
6
,
Dong Liu
2
,
Yadong Mu
4
,
Mingkui Tan
5
,
Xinggang Wang
3
,
Wen-Yu Liu
3
,
Bin Xiao
7
1
Microsoft Research, Beijing, P.R. China
|
7
Microsoft, Redmond, WA, USA
|
Publication type: Journal Article
Publication date: 2021-10-01
scimago Q1
wos Q1
SJR: 3.910
CiteScore: 35.0
Impact factor: 18.6
ISSN: 01628828, 21609292, 19393539
PubMed ID:
32248092
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics
Software
Computer Vision and Pattern Recognition
Abstract
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions
in series
(e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams
in parallel
and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at
https://github.com/HRNet
.
Found
Nothing found, try to update filter.
Found
Nothing found, try to update filter.
Top-30
Journals
|
20
40
60
80
100
120
140
160
180
|
|
|
Lecture Notes in Computer Science
169 publications, 5.24%
|
|
|
IEEE Access
102 publications, 3.16%
|
|
|
Remote Sensing
98 publications, 3.04%
|
|
|
IEEE Transactions on Geoscience and Remote Sensing
87 publications, 2.7%
|
|
|
Sensors
82 publications, 2.54%
|
|
|
IEEE Transactions on Pattern Analysis and Machine Intelligence
71 publications, 2.2%
|
|
|
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
66 publications, 2.05%
|
|
|
Neurocomputing
47 publications, 1.46%
|
|
|
IEEE Transactions on Image Processing
43 publications, 1.33%
|
|
|
IEEE Transactions on Circuits and Systems for Video Technology
42 publications, 1.3%
|
|
|
Applied Sciences (Switzerland)
36 publications, 1.12%
|
|
|
IEEE Transactions on Instrumentation and Measurement
36 publications, 1.12%
|
|
|
Scientific Reports
35 publications, 1.09%
|
|
|
Expert Systems with Applications
35 publications, 1.09%
|
|
|
Engineering Applications of Artificial Intelligence
33 publications, 1.02%
|
|
|
Electronics (Switzerland)
32 publications, 0.99%
|
|
|
IEEE Transactions on Multimedia
31 publications, 0.96%
|
|
|
International Journal of Computer Vision
30 publications, 0.93%
|
|
|
Pattern Recognition
30 publications, 0.93%
|
|
|
IEEE Geoscience and Remote Sensing Letters
29 publications, 0.9%
|
|
|
IEEE Transactions on Intelligent Transportation Systems
26 publications, 0.81%
|
|
|
Biomedical Signal Processing and Control
24 publications, 0.74%
|
|
|
ISPRS Journal of Photogrammetry and Remote Sensing
23 publications, 0.71%
|
|
|
International Journal of Applied Earth Observation and Geoinformation
22 publications, 0.68%
|
|
|
IEEE Robotics and Automation Letters
22 publications, 0.68%
|
|
|
Computers in Biology and Medicine
21 publications, 0.65%
|
|
|
Computers and Electronics in Agriculture
21 publications, 0.65%
|
|
|
Knowledge-Based Systems
21 publications, 0.65%
|
|
|
IEEE Journal of Biomedical and Health Informatics
21 publications, 0.65%
|
|
|
20
40
60
80
100
120
140
160
180
|
Publishers
|
200
400
600
800
1000
1200
1400
|
|
|
Institute of Electrical and Electronics Engineers (IEEE)
1383 publications, 42.88%
|
|
|
Elsevier
585 publications, 18.14%
|
|
|
Springer Nature
514 publications, 15.94%
|
|
|
MDPI
345 publications, 10.7%
|
|
|
Association for Computing Machinery (ACM)
65 publications, 2.02%
|
|
|
Taylor & Francis
46 publications, 1.43%
|
|
|
Wiley
39 publications, 1.21%
|
|
|
Frontiers Media S.A.
34 publications, 1.05%
|
|
|
SPIE-Intl Soc Optical Eng
25 publications, 0.78%
|
|
|
SAGE
24 publications, 0.74%
|
|
|
Institution of Engineering and Technology (IET)
15 publications, 0.47%
|
|
|
IOP Publishing
15 publications, 0.47%
|
|
|
Public Library of Science (PLoS)
12 publications, 0.37%
|
|
|
Hindawi Limited
9 publications, 0.28%
|
|
|
Tsinghua University Press
7 publications, 0.22%
|
|
|
Optica Publishing Group
7 publications, 0.22%
|
|
|
Oxford University Press
6 publications, 0.19%
|
|
|
American Society of Civil Engineers (ASCE)
4 publications, 0.12%
|
|
|
Science in China Press
4 publications, 0.12%
|
|
|
Cold Spring Harbor Laboratory
4 publications, 0.12%
|
|
|
World Scientific
4 publications, 0.12%
|
|
|
PeerJ
3 publications, 0.09%
|
|
|
American Chemical Society (ACS)
3 publications, 0.09%
|
|
|
ASME International
3 publications, 0.09%
|
|
|
Society of Exploration Geophysicists
3 publications, 0.09%
|
|
|
Pleiades Publishing
2 publications, 0.06%
|
|
|
AIP Publishing
2 publications, 0.06%
|
|
|
Tech Science Press
2 publications, 0.06%
|
|
|
Institute of Electronics, Information and Communications Engineers (IEICE)
2 publications, 0.06%
|
|
|
200
400
600
800
1000
1200
1400
|
- 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
3.2k
Total citations:
3225
Citations from 2024:
1806
(56%)
Cite this
GOST |
RIS |
BibTex |
MLA
Cite this
GOST
Copy
Wang J. et al. Deep High-Resolution Representation Learning for Visual Recognition // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2021. Vol. 43. No. 10. pp. 3349-3364.
GOST all authors (up to 50)
Copy
Wang J., Sun K., Cheng T., Jiang B., Deng C., Zhao Yang, Liu D., Mu Y., Tan M., Wang X., Liu W., Xiao B. Deep High-Resolution Representation Learning for Visual Recognition // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2021. Vol. 43. No. 10. pp. 3349-3364.
Cite this
RIS
Copy
TY - JOUR
DO - 10.1109/TPAMI.2020.2983686
UR - https://doi.org/10.1109/TPAMI.2020.2983686
TI - Deep High-Resolution Representation Learning for Visual Recognition
T2 - IEEE Transactions on Pattern Analysis and Machine Intelligence
AU - Wang, Jing-Dong
AU - Sun, Ke
AU - Cheng, Tianheng
AU - Jiang, Borui
AU - Deng, Chaorui
AU - Zhao Yang
AU - Liu, Dong
AU - Mu, Yadong
AU - Tan, Mingkui
AU - Wang, Xinggang
AU - Liu, Wen-Yu
AU - Xiao, Bin
PY - 2021
DA - 2021/10/01
PB - Institute of Electrical and Electronics Engineers (IEEE)
SP - 3349-3364
IS - 10
VL - 43
PMID - 32248092
SN - 0162-8828
SN - 2160-9292
SN - 1939-3539
ER -
Cite this
BibTex (up to 50 authors)
Copy
@article{2021_Wang,
author = {Jing-Dong Wang and Ke Sun and Tianheng Cheng and Borui Jiang and Chaorui Deng and Zhao Yang and Dong Liu and Yadong Mu and Mingkui Tan and Xinggang Wang and Wen-Yu Liu and Bin Xiao},
title = {Deep High-Resolution Representation Learning for Visual Recognition},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2021},
volume = {43},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
month = {oct},
url = {https://doi.org/10.1109/TPAMI.2020.2983686},
number = {10},
pages = {3349--3364},
doi = {10.1109/TPAMI.2020.2983686}
}
Cite this
MLA
Copy
Wang, Jing-Dong, et al. “Deep High-Resolution Representation Learning for Visual Recognition.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 10, Oct. 2021, pp. 3349-3364. https://doi.org/10.1109/TPAMI.2020.2983686.