Search

Your search keyword '"SHI Qingxuan"' showing total 223 results
Start Over Author "SHI Qingxuan"
223 results on '"SHI Qingxuan"'

23. Cascade Scale-Aware Distillation Network for Lightweight Remote Sensing Image Super-Resolution

Author

Ji, Haowei, Di, Huijun, Wang, Shunzhou, Shi, Qingxuan, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Yu, Shiqi, editor, Zhang, Zhaoxiang, editor, Yuen, Pong C., editor, Han, Junwei, editor, Tan, Tieniu, editor, Guo, Yike, editor, Lai, Jianhuang, editor, and Zhang, Jianguo, editor

Published
2022
Full Text
View/download PDF

32. Edge Guided Attention Based Densely Connected Network for Single Image Super-Resolution

Author

Wang, Zijian, Lu, Yao, Shi, Qingxuan, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Mantoro, Teddy, editor, Lee, Minho, editor, Ayu, Media Anugerah, editor, Wong, Kok Wai, editor, and Hidayanto, Achmad Nizar, editor

Published
2021
Full Text
View/download PDF

33. Seismic performance of external diaphragm joints of steel beam-to-CFST column encasing fiber reinforced polymer confined UHPC core.

Author

Wang, Dan, Tao, Yi, Gu, Jinben, Chen, Zhiheng, and Shi, Qingxuan

Subjects
COMPOSITE columns, CONCRETE-filled tubes, HIGH strength concrete, SHEAR (Mechanics), COMPOSITE construction
Abstract

A novel composite column was introduced by integrating a concrete-filled steel tube column encasing a Fiber Reinforced Polymer (FRP) confined ultra high performance concrete (UHPC) core. In this paper, the seismic performance of four SCF-UHPC composite column-to-steel beam connections using external diaphragm joints was experimentally investigated under the quasi-static test. All specimens failed due to the formation of plastic hinges at the beams and the tearing failure on the beam flanges at the plastic hinge zone. The local buckling at the column end and the panel zone was observed for the specimens receiving the higher axial compression ratio. The increase of FRP tube thickness is more effective in improving the ductility and energy dissipation capacity of the joints than increasing the UHPC core diameter. On the contrary, increasing the UHPC core diameter led to better resistance to the shear deformation of the panel zone. The proportion of shear deformation to the total deformation of the panel zone and the strain distributions were investigated to determine the effect of each component. The composite column in the panel zone mainly carried the compression-bending effort, and the external diaphragm mainly took the shear effort. All joints were eventually classified as semi-rigid type joints, according to the initial rotational stiffness. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

44. Self-Supervised Interactive Image Segmentation

Author

Shi, Qingxuan, Li, Yihang, Di, Huijun, and Wu, Enyi

Abstract

Although interactive image segmentation techniques have made significant progress, supervised learning-based methods rely heavily on large-scale labeled data which is difficult to obtain in certain domains such as medicine, biology, etc. Models trained on natural images also struggle to achieve satisfactory results when directly applied to these domains. To solve this dilemma, we propose a Self-supervised Interactive Segmentation (SIS) method that achieves superior generalization performance. By clustering features from unlabeled data, we obtain classifiers that assign pseudo-labels to pixels in images. After refinement by super-pixel voting, these pseudo-labels are then used to train our segmentation network. To enable our network to better adapt to cross-domain images, we introduce correction learning and anti-forgetting regularization to conduct test-time adaptation. Our experiment results on five datasets show that our approach significantly outperforms other interactive segmentation methods across natural image datasets in the same conditions and achieves even better performance than some supervised methods when across to medical image domain. The code and models are available at https://github.com/leal0110/SIS.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results