Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Shang-Hua Gao"'
Autor:
Hong Su, Wenkai Wang, Zongyang Du, Zhenling Peng, Shang‐Hua Gao, Ming‐Ming Cheng, Jianyi Yang
Publikováno v:
Advanced Science, Vol 8, Iss 24, Pp n/a-n/a (2021)
Abstract The accuracy of de novo protein structure prediction has been improved considerably in recent years, mostly due to the introduction of deep learning techniques. In this work, trRosettaX, an improved version of trRosetta for protein structure
Externí odkaz:
https://doaj.org/article/1adb7fd7e3664787b1bbb69a39ad6da1
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:8006-8021
CNN-based salient object detection (SOD) methods achieve impressive performance. However, the way semantic information is encoded in them and whether they are category-agnostic is less explored. One major obstacle in studying these questions is the f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f7426383237b40a15b62a96760834f2
https://doi.org/10.1109/tpami.2021.3107956
https://doi.org/10.1109/tpami.2021.3107956
Autor:
Zongyang Du, Wenkai Wang, Zhenling Peng, Shang-Hua Gao, Jianyi Yang, Ming-Ming Cheng, Hong Su
Publikováno v:
Advanced Science, Vol 8, Iss 24, Pp n/a-n/a (2021)
Advanced Science
Advanced Science
The accuracy of de novo protein structure prediction has been improved considerably in recent years, mostly due to the introduction of deep learning techniques. In this work, trRosettaX, an improved version of trRosetta for protein structure predicti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0a057650a7fd84319e83e69d8048be7d
https://doaj.org/article/1adb7fd7e3664787b1bbb69a39ad6da1
https://doaj.org/article/1adb7fd7e3664787b1bbb69a39ad6da1
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9ca9333e0aab64641ca3f20720528280
https://doi.org/10.1109/iccv48922.2021.00489
https://doi.org/10.1109/iccv48922.2021.00489
Publikováno v:
CVPR
Batch Normalization (BatchNorm) has become the default component in modern neural networks to stabilize training. In BatchNorm, centering and scaling operations, along with mean and variance statistics, are utilized for feature standardization over t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ce457697cb7330ce29bdf37991f41a1
https://doi.org/10.1109/cvpr46437.2021.00856
https://doi.org/10.1109/cvpr46437.2021.00856
Publikováno v:
Journal of Communications and Information Networks. 4:89-100
Orbital angular momentum (OAM) based radio vortex wireless communications have received much attention recently because it can significantly increase the spectrum efficiency. The uniform circular array (UCA) is a simple antenna structure for high spe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b926334216303314aa4b2cea2c9c59a2
https://doi.org/10.23919/jcin.2019.8917875
https://doi.org/10.23919/jcin.2019.8917875
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 30
Recently, the coronavirus disease 2019 (COVID-19) has caused a pandemic disease in over 200 countries, influencing billions of humans. To control the infection, identifying and separating the infected people is the most crucial step. The main diagnos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4907a628be8e8572a0c7c120a55e6610
https://pubmed.ncbi.nlm.nih.gov/33600316
https://pubmed.ncbi.nlm.nih.gov/33600316
Autor:
Zhuqing Jiang, Qishuo Lu, Aidong Men, Shang-Hua Gao, Zhengxin Zeng, Qiulin Zhang, Jia'nan Han
Publikováno v:
IJCAI
Many effective solutions have been proposed to reduce the redundancy of models for inference acceleration. Nevertheless, common approaches mostly focus on eliminating less important filters or constructing efficient operations, while ignoring the pat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87ab6b30bdd81fa8effb4f0decca24ec
http://arxiv.org/abs/2006.12085
http://arxiv.org/abs/2006.12085
Publikováno v:
CVPR
Extracting road graphs from aerial images automatically is more efficient and costs less than from field acquisition. This can be done by a post-processing step that vectorizes road segmentation predicted by CNN, but imperfect predictions will result
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de408cd96cf7b1a9c59ad89665f0fde8
https://doi.org/10.1109/cvpr42600.2020.00893
https://doi.org/10.1109/cvpr42600.2020.00893