Zhongwei Zhao

Zhongwei Zhao

Auto-generated profile, based on publicly available information

Zhongwei Zhao

Shandong University, Jinan, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2022 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
ZZZhongwei Zhao
Zhongwei Zhao
RSRan Song
Ran Song
QZQian Zhang
Qian Zhang
PDPeng Duan
Peng Duan
YZYoumei Zhang
Youmei Zhang
To cope with the problem caused by inadequate training data, many person re-identification (re-id) methods exploit generative adversarial networks (GAN) for data augmentation, where the training of GAN is typically independent of that of the re-id model. The coupling relation between them that probably brings in a performance gain of re-id is thus ignored. In this work, we propose a general framework, namely JoT-GAN, to jointly train GAN and the re-id model. It can simultaneously achieve the optima of both the generator and the re-id model, where the training is guided by each other through a discriminator. The re-id model is boosted for two reasons: (1) the adversarial training encourages it to fool the discriminator, and (2) the generated samples augment the training data. Extensive results on benchmark datasets show that for the re-id model trained with the identification loss as well as the triplet loss, the proposed joint training framework outperforms existing methods with separate training and achieves state-of-the-art re-id performance.

12 March 2021
Verified
Conference Paper
Closed access
AZAndrew Zhang
Andrew Zhang
SYShuilin Yan
Shuilin Yan
YLYang Liu
Yang Liu
WZWeixiang Zhu
Weixiang Zhu
ZZZhongwei Zhao
Zhongwei Zhao
Power load forecasting is an important component of modern power system project which is the foundation of economic operation. In order to effectively improve the precision of short period load forecasting, traditional neural network has slow convergence and easily falling into local optimum in the practical application. This paper proposes a novel neural network load forecasting algorithm with wavelet neural network and self-adaptive momentum factor. This algorithm combines the characteristics in the wavelet transform's time domain and frequency domain. By adding an adaptive momentum factor, the new algorithm has better stability and higher convergence rate. By comparing three different prediction models, the simulation results show that the improved algorithm model has higher convergence accuracy.