Institution
University of Macau
Education•Macao, Macau, China•
About: University of Macau is a education organization based out in Macao, Macau, China. It is known for research contribution in the topics: Population & Control theory. The organization has 6636 authors who have published 18324 publications receiving 327384 citations. The organization is also known as: UM & UMAC.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: Results demonstrate that the stacked supervised autoencoders-based face representation significantly outperforms the commonly used image representations in single sample per person face recognition, and it achieves higher recognition accuracy compared with other deep learning models, including the deep Lambertian network.
Abstract: This paper targets learning robust image representation for single training sample per person face recognition. Motivated by the success of deep learning in image representation, we propose a supervised autoencoder, which is a new type of building block for deep architectures. There are two features distinct our supervised autoencoder from standard autoencoder. First, we enforce the faces with variants to be mapped with the canonical face of the person, for example, frontal face with neutral expression and normal illumination; Second, we enforce features corresponding to the same person to be similar. As a result, our supervised autoencoder extracts the features which are robust to variances in illumination, expression, occlusion, and pose, and facilitates the face recognition. We stack such supervised autoencoders to get the deep architecture and use it for extracting features in image representation. Experimental results on the AR, Extended Yale B, CMU-PIE, and Multi-PIE data sets demonstrate that by coupling with the commonly used sparse representation-based classification, our stacked supervised autoencoders-based face representation significantly outperforms the commonly used image representations in single sample per person face recognition, and it achieves higher recognition accuracy compared with other deep learning models, including the deep Lambertian network, in spite of much less training data and without any domain information. Moreover, supervised autoencoder can also be used for face verification, which further demonstrates its effectiveness for face representation.
205 citations
••
TL;DR: The fractional diffusion equation is discretized by the implicit finite difference scheme with the shifted Grunwald formula and the coefficient matrix possesses the Toeplitz-like structure and a multigrid method is proposed to solve the resulting system.
204 citations
••
30 Dec 2019
TL;DR: A synopsis of the recent literature exploring the relationship between quercetin and cognitive performance in Alzheimer’s disease and its potential as a lead compound in clinical applications is provided.
Abstract: Quercetin is a flavonoid with notable pharmacological effects and promising therapeutic potential. It is widely distributed among plants and found commonly in daily diets predominantly in fruits and vegetables. Neuroprotection by quercetin has been reported in several in vitro studies. It has been shown to protect neurons from oxidative damage while reducing lipid peroxidation. In addition to its antioxidant properties, it inhibits the fibril formation of amyloid-β proteins, counteracting cell lyses and inflammatory cascade pathways. In this review, we provide a synopsis of the recent literature exploring the relationship between quercetin and cognitive performance in Alzheimer’s disease and its potential as a lead compound in clinical applications.
204 citations
••
TL;DR: For a high-order considered system, the attention is focused on the construction of a reduced-order model, which not only approximates the original system well with a Hankel-norm performance but translates it into a lower dimensional fuzzy switched system as well.
Abstract: In this paper, the model approximation problem is investigated for a Takagi–Sugeno fuzzy switched system with stochastic disturbance. For a high-order considered system, our attention is focused on the construction of a reduced-order model, which not only approximates the original system well with a Hankel-norm performance but translates it into a lower dimensional fuzzy switched system as well. By using the average dwell time approach and the piecewise Lyapunov function technique, a sufficient condition is first proposed to guarantee the mean-square exponential stability with a Hankel-norm error performance for the error system. The model approximation is then converted into a convex optimization problem by using a linearization procedure. Finally, simulations are provided to illustrate the effectiveness of the proposed theory.
203 citations
••
TL;DR: The SAR analysis of flavonoids on influenza virus NAs revealed that for good inhibitory effect, the 4'-OH, 7-OH, C4O, and C2C3 functionalities were essential, and the presence of a glycosylation group greatly reduced NA inhibition.
203 citations
Authors
Showing all 6766 results
Name | H-index | Papers | Citations |
---|---|---|---|
Henry T. Lynch | 133 | 925 | 86270 |
Chu-Xia Deng | 125 | 444 | 57000 |
H. Vincent Poor | 109 | 2116 | 67723 |
Peng Chen | 103 | 918 | 43415 |
George F. Gao | 102 | 793 | 82219 |
MengChu Zhou | 96 | 1124 | 36969 |
Gang Li | 93 | 486 | 68181 |
Rob Law | 81 | 714 | 31002 |
Zongjin Li | 80 | 630 | 22103 |
Han-Ming Shen | 80 | 237 | 27410 |
Heng Li | 79 | 745 | 23385 |
Lionel M. Ni | 75 | 466 | 28770 |
C. L. Philip Chen | 74 | 482 | 20223 |
Chun-Su Yuan | 72 | 397 | 21089 |
Joao P. Hespanha | 72 | 418 | 39004 |