Search

Your search keyword '"Xu, Shimei"' showing total 358 results
Start Over Author "Xu, Shimei"
358 results on '"Xu, Shimei"'

4. BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Images

Author

Xu, Gao, Long, Yuanpeng, Liu, Siwei, Yang, Lijia, Xu, Shimei, Yao, Xiaoming, and Shu, Kunxian

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

The flow-based generative model is a deep learning generative model, which obtains the ability to generate data by explicitly learning the data distribution. Theoretically its ability to restore data is stronger than other generative models. However, its implementation has many limitations, including limited model design, too many model parameters and tedious calculation. In this paper, a bi-parallel linear flow model for facial emotion generation from emotion set images is constructed, and a series of improvements have been made in terms of the expression ability of the model and the convergence speed in training. The model is mainly composed of several coupling layers superimposed to form a multi-scale structure, in which each coupling layer contains 1*1 reversible convolution and linear operation modules. Furthermore, this paper sorted out the current public data set of facial emotion images, made a new emotion data, and verified the model through this data set. The experimental results show that, under the traditional convolutional neural network, the 3-layer 3*3 convolution kernel is more conducive to extracte the features of the face images. The introduction of principal component decomposition can improve the convergence speed of the model., Comment: 20 pages, 10 figures

Published
2021

5. An optimized Capsule-LSTM model for facial expression recognition with video sequences

Author

Liu, Siwei, Long, Yuanpeng, Xu, Gao, Yang, Lijia, Xu, Shimei, Yao, Xiaoming, and Shu, Kunxian

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

To overcome the limitations of convolutional neural network in the process of facial expression recognition, a facial expression recognition model Capsule-LSTM based on video frame sequence is proposed. This model is composed of three networks includingcapsule encoders, capsule decoders and LSTM network. The capsule encoder extracts the spatial information of facial expressions in video frames. Capsule decoder reconstructs the images to optimize the network. LSTM extracts the temporal information between video frames and analyzes the differences in expression changes between frames. The experimental results from the MMI dataset show that the Capsule-LSTM model proposed in this paper can effectively improve the accuracy of video expression recognition., Comment: 14pages,4 figurews

Published
2021

40. Multiple promotion effect of mixed solvents on the oxidative degradation of thermosetting polymers.

Author

Long, Yuwei, Su, Zhishan, Bai, Lan, Zhao, Xu, An, Wenli, Liu, Xuehui, Xu, Shimei, and Wang, Yu-Zhong

Subjects
THERMOSETTING polymers, SOLVENTS, POLYMERS, SMALL molecules, POLYMER degradation, ORGANIC solvents, ENERGY conversion
Abstract

The solvent effect has been widely explored in small molecule reactions. However, understanding of the solvent effect on the degradation of thermosetting polymers, especially when it comes to mixed solvents, remains largely elusive. Here the effect of mixed solvents on the oxidative degradation of typical epoxy thermosets is presented. An enhancement effect of the swelling and diffusion was observed in mixed solvents of water and organic solvents, with a higher interaction energy. Besides, the introduction of an organic solvent can enhance the oxidation activities of an oxidant cerium ammonium nitrate aqueous solution. The multiple effects greatly promote the degradation of epoxy thermosets and complete degradation was even achieved at room temperature. This unconventional result reveals the synergistic effects of mixed solvents in polymer degradation and opens a new insight on polymer recycling. It is expected to guide polymers to achieve high value-added recovery and conversion with low energy consumption. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

49. Multifunctional Materials from Aerobic Degradation of Epoxy Thermoset via Phosphotungstic Acid‐Involved Activation and Bonding.

Author

Zhou, Xuelian, Zhang, Shun, An, Wenli, Zhao, Xu, Long, Yuwei, Liu, Xuehui, Xu, Shimei, and Wang, Yu‐Zhong

Subjects
CHEMICAL recycling, MOLECULAR weights, CATALYTIC oxidation, EPOXY resins, HYDROGEN bonding, WIND turbines
Abstract

The growing scale of production of wind turbines represents a big challenge for chemical recycling of amine‐cured epoxy resin (EP) to achieve high‐efficiency degradation and high‐value utilization of degradation products. Here, H2O2/phosphotungstic acid (HPW) catalytic oxidation system is demonstrated to completely degrade EP thermoset with the solid recovery rate of 96% at a reaction temperature of 80 °C for 4 h. Owing to protonation and bonding effect of HPW to the amine groups, the degradation products had a weight‐average molecular weight of 4285 with narrow molecular weight distribution. They were used as dye adsorption blend films and supramolecular adhesives based on hydrogen bonding and coordination bonding respectively. The work demonstrates a feasible and promising method to recover the EP thermoset into high‐performance materials. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results