Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Yujie Huang"'
Autor:
Wei Mei, Yujie Huang, Shuang Zhang, Shao-Jie Gao, Jia Sun, Jia-Yan Li, Jiayi Wu, Dai-Qiang Liu
Publikováno v:
Current Neuropharmacology. 20:223-253
Great progress has been made in specifically identifying the central neural circuits (CNCs) of the core body temperature (Tcore), sleep-wakefulness states (SWs), and general anesthesia states (GAs), mainly utilizing optogenetic or chemogenetic manipu
Publikováno v:
IEEE Transactions on Multimedia. 24:3978-3988
Recently, Deep Convolutional Neural Networks (DCNNs) have achieved remarkable progress in computer vision community, including in style transfer tasks. Normally, most methods feed the full image to the DCNN. Although highquality results can be achiev
Autor:
Zhao Chenyang, Keji Zhou, Haidong Tian, Deyang Chen, Minge Jing, Jinbei Fang, Xiaoyang Zeng, Qi Liu, Xiaoyong Xue, Yujie Huang, Jiang Jingwen, Xiankui Xiong, Jun Han
Publikováno v:
IEEE Transactions on Circuits and Systems II: Express Briefs. 68:2932-2936
In this work, a ReRAM-based energy-efficient CIM accelerator is presented with two techniques for edge AI applications. Firstly, a circuit-algorithm co-design scheme is proposed to realize fully analog processing, which improves the energy efficiency
Autor:
Junying Zeng, Gan Junying, Vincenzo Piuri, Qin Chuanbo, Yujie Huang, Fan Wang, Zhu Jingming, Yucong Chen, Ruggero Donida Labati, Fabio Scotti, Zhu Boyuan, Yingbo Wang, Yikui Zhai
Publikováno v:
IEEE Access, Vol 9, Pp 303-316 (2021)
Because the existing finger vein segmentation networks are too large and not suitable for implementation in mobile terminals, the reduction of the parameters of the lightweight network leads to the reduction of the segmentation index, and the long-ru
Publikováno v:
ISCAS
Since deep learning was introduced into style transfer, remarkable results have been achieved in it and it is widely used in multimedia fields, such as photography. However, the computational costs of the existing state-of-the-art (SOTA) arbitrary st
Autor:
Yujie Huang, Xiaoxiang Li, Meng Chen, Quanliang Cao, Qi Chen, Xiaotao Han, Zhipeng Lai, Qingshan Cao, Liang Li, Ning Liu
Publikováno v:
The International Journal of Advanced Manufacturing Technology. 101:2585-2607
Due to its simplicity and clear physical meaning, the analytical method is attractive for analyzing the multiphysics of electromagnetic forming; however, the reliability of the analytical method is of great concern due to numerous simplifications. Ta
Publikováno v:
Proceedings of the 2021 5th International Seminar on Education, Management and Social Sciences (ISEMSS 2021).
Publikováno v:
CSAE
Aiming at the problem that traditional convolutional neural networks cannot fully capture text features during feature extraction, and a single model cannot effectively extract deep text features, this paper proposes a text sentiment classification m
Publikováno v:
ISCAS
Finding enough accurate matching points is key for image stitching. However, the existing state-of-the-art algorithms fail to find enough accurate matching points when facing the challenge where detectable features are not obvious. In this paper, a n
Publikováno v:
2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications( AEECA).
In view of the simple structure of a single neural network model, the traditional convolutional neural network cannot fully extract deep text features. This paper proposes a text sentiment classification based on Attention Mechanism and Decomposition