Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Xianyi Zhu"'
Publikováno v:
IEEE Access, Vol 8, Pp 50995-51007 (2020)
Inverse halftoning and image expanding refer to problems to restore the pixel values of images from compressed images of smaller bit depth. Since these two problems are ill-posed, there are few perfect solutions. Recently, deep convolutional neural n
Externí odkaz:
https://doaj.org/article/07da109d58e141b1890aaab1c0774f42
Publikováno v:
Engineering Analysis with Boundary Elements. 143:710-718
Publikováno v:
Neurocomputing. 463:525-534
Convolutional neural networks (CNNs) based super-resolution (SR) methods have achieved remarkable progress in recent years. Most of these methods assume that the degradation is known and fixed, such as bicubic downsampling. However, the performance o
Publikováno v:
Neurocomputing. 454:350-360
Recently, depth map super-resolution (DSR) has obtained remarkable performance with the development of convolutional neural networks (CNNs). High-resolution (HR) depth map can be inferred from a low-resolution (LR) one with the guidance of its corres
Autor:
Yuanlong Guo, Lijie Hu, Lihua Zhang, Guanglong Zou, Songmiao Liang, Haibo Xie, Xianyi Zhu, Qin Chen, Michael North
Publikováno v:
International Journal of Biological Macromolecules. 180:792-803
Facile preparation of functional hydrogel materials for environmental catalysis is a hot research topic of soft materials science and green catalysis. In this study, a carboxylcellulose hydrogel confined Fe3O4 nanoparticles composite catalyst (Fe3O4@
Publikováno v:
Green Chemistry. 23:9922-9934
The facile design and preparation of polyelectrolytes is a frontier topic in the fields of polymer science, energy storage devices and catalysis. Herein, linear water soluble cellulosic poly(protic ionic liquid) (CPIL) electrolytes were facilely and
Publikováno v:
Future Generation Computer Systems. 112:58-66
Locating the neurofibromatosis boundaries is one of the most challenging tasks due to the properties of low contrast and irregular blurred boundaries. To handle this problem, we propose Deep Parametric Active Contours (DPAC), a novel end-to-end frame
Publikováno v:
IET Image Processing. 14:1710-1715
Fingerprints are widely used for biometric recognition. However, many spoofing attacks based on an artificially made fingerprint occur. In this study, the authors propose an approach to detect fingerprint liveness which uses the guided filtering and
Publikováno v:
Multimedia Tools and Applications. 79:33891-33906
Sketch segmentation and labeling face two challenges: few samples and few features. 3D data-driven methods use additional labeled 3D meshes to increase samples. However, they are not feasible for the abstract sketches that have no corresponding 3D me
Publikováno v:
Multimedia Tools and Applications. 79:1585-1602
Accurate and fast sketch segmentation and labeling is a hard task, since sketches have much fewer features than natural images. This paper proposes a novel hybrid approach for fast automatic sketch labeling, which is based on convolutional neural net