Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Ruifei He"'
While self-training has advanced semi-supervised semantic segmentation, it severely suffers from the long-tailed class distribution on real-world semantic segmentation datasets that make the pseudo-labeled data bias toward majority classes. In this p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53ee05e3ff8f36d3052a785d677b6eac
Autor:
Jilin Li, Jiangning Zhang, Ruifei He, Donghao Luo, Feiyue Huang, Chengjie Wang, Yong Liu, Liang Liu, Ying Tai, Yabiao Wang
Publikováno v:
CVPR
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods. However, the objective of unsupervised learning is likely to be unreliable in challenging scenes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bae55b33370274880edaff0e0e91290a
https://doi.org/10.1109/cvpr42600.2020.00652
https://doi.org/10.1109/cvpr42600.2020.00652
Publikováno v:
2019 22nd International Conference on Electrical Machines and Systems (ICEMS).
This paper proposed a unified control strategy for variable speed pumped storage power station based on double-fed induction generator (DFIG) under different grid conditions including the ideal grid, symmetrical voltage dips and asymmetrical voltage
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dcf0f9ab852e385f733fc3e241e37d55
https://doi.org/10.1109/icems.2019.8921824
https://doi.org/10.1109/icems.2019.8921824