Jun Wang

Dr. Jun Wang

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 March 2020 in Journal of Cleaner Production
Verified
Journal Article
Closed access
BYBaoqin Yu
Baoqin Yu
JWJun Wang
Jun Wang
XLXinman Lu
Xinman Lu
HYHongtao Yang
Hongtao Yang

1 August 2019 in Journal of Cleaner Production
Verified
Journal Article
Closed access
JWJun Wang
Jun Wang
SYSong Yao
Song Yao
JSJiachuan Sheng
Jiachuan Sheng
HYHongtao Yang
Hongtao Yang

18 January 2024 in European Journal of Operational Research
Verified
Journal Article
Closed access
QZQian Zhang
Qian Zhang
YLYongjian Li
Yongjian Li
PHPengwen Hou
Pengwen Hou
JWJun Wang
Jun Wang

23 January 2023 in Computers & Industrial Engineering
Verified
Journal Article
Closed access
JWJun Wang
Jun Wang
QZQian Zhang
Qian Zhang
PHPengwen Hou
Pengwen Hou
QLQinghua Li
Qinghua Li

11 November 2019 in IEEE Access
Verified
Journal Article
Open access
JSJiachuan Sheng
Jiachuan Sheng
CSCaifeng Song
Caifeng Song
JWJun Wang
Jun Wang
YHYahong Han
Yahong Han
Chinese painting is one of the most important cultural heritages. However, creating a Chinese painting usually requires specific skills, patience, and years of professional training. Moreover, most existing style transfer methods mainly focus on photograph or western painting, and there are intrinsic differences between Chinese and western paintings. To this end, we propose a novel algorithm of Chinese painting style transfer (CPST) towards transferring with unique ink and wash characteristics, which automatically generates Chinese paintings with machine learning technology. In this paper, firstly, comparing Chinese paintings with western works, we set up four key restrictions in the style transfer, i.e., with special considerations of typical ink and wash features, including brush stroke, space reservation, ink tone with diffusion and yellowing. In order to incorporate these restrictions into the transferring convolutional neural networks (CNN), we separate different layers of the CNN into layers of style and content, so as to faithfully reserve the style of the reference image. Secondly, as Chinese paintings can be divided into fine brushwork and freehand brushwork, to cope with diverse painting skills, we devise different strategies to transfer not only the ink tone but also the painting skills to the target images. Experiments show that taking the aesthetic characteristics of Chinese painting style as reference, our results are more visually satisfactory and successfully overcome spillovers.

3 April 2022 in International Journal of Electronic Commerce
Verified
Journal Article
Closed access
JWJun Wang
Jun Wang
QZQian Zhang
Qian Zhang
PHPengwen Hou
Pengwen Hou
In platform selling, platforms commonly charge third-party sellers a commission fee, which affects sellers’ decision making and platforms’ contract choice. This study explores this choice where a platform privately knows the market size and intends to signal to a seller. We aim to provide researchers and platform-selling practitioners insights into contract and information strategies. The result shows that the fixed-fee contract leads to either a costly or a costless signaling scenario. In costly scenarios, the high-demand platform must downward distort the fixed rent to distinguish itself from the low-demand platform. This distortion results in a different consensus on two players’ contract preference when the commission rate in the proportional-fee contract is exogenous. Under symmetric information, consensus is achieved only on the proportional-fee contract. However, in asymmetric information settings, this consensus may arise on fixed-fee contracts if market uncertainty is high. Furthermore, the comparison of information strategies reveals that players can reach an agreement on both the information-sharing strategy and the proportional-fee contract under certain conditions. When the platform endogenously determines the commission rate, this decision making can also signal demand type, and only the proportional-fee contract leads to a win–win outcome.