Shibin Wang

Dr. Shibin Wang


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
10 May 2020 in Peer-to-Peer Networking and Applications
Verified
Journal Article
Closed access
PDF file
SWShibin Wang
Shibin Wang
KMKele Mao
Kele Mao
FZFuirui Zhan
Fuirui Zhan
Dong LiuDong Liu
Dong Liu


22 July 2023 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
SWShibin Wang
Shibin Wang
XMXueshu Mei
Xueshu Mei
PKPengshuai Kang
Pengshuai Kang
YLYan Li
Yan Li
Dong LiuDong Liu
Dong Liu

12 September 2025 in npj Heritage Science
Verified
Journal Article
Open access
PDF file
RWRan Wu
Ran Wu
SWShibin Wang
Shibin Wang
XLXueshan Li
Xueshan Li
Dong LiuDong Liu
Dong Liu
Oracle Bone Inscriptions (OBI), the earliest systematic writing in China, are crucial for understanding early Chinese civilization. However, many inscriptions remain undeciphered due to limited data, complex glyphs, and weak semantic consistency. Although Generative Adversarial Networks (GAN) and Diffusion Models have introduced new possibilities to the field, most existing methods primarily focus on visual features and lack semantic integration. To address this challenge, we propose DCSD-OBI, a Dual-Conditional Stable Diffusion model that integrates OBI images and modern Chinese text during reverse diffusion to jointly learn structural and semantic features, thereby improving character generation accuracy. To reduce training cost while preserving generative quality, we adopt Low-Rank Adaptation (LoRA) to fine-tune only the U-Net’s cross-attention modules. Furthermore, we replace CLIP with Chinese-CLIP, a version tailored for the Chinese language, to improve cross-modal semantic consistency. Experiments results show DCSD-OBI improves decipherment accuracy by 11%, highlighting its effectiveness and potential for advancing OBI research.

1 January 2024
Verified
Conference Paper
Open access
PDF file
SWShibin Wang
Shibin Wang
WGWenjie Guo
Wenjie Guo
YXYubo Xu
Yubo Xu
DLDong Liu
Dong Liu
XLXueshan Li
Xueshan Li
Shibin Wang, Wenjie Guo, Yubo Xu, Dong Liu, Xueshan Li. Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024). 2024.

29 May 2025 in Electronics
Verified
Journal Article
Open access
PDF file
SWShibin Wang
Shibin Wang
GXGuo Xuening
Guo Xuening
WGWenjie Guo
Wenjie Guo
Image inpainting approaches have made considerable progress with the assistance of generative adversarial networks (GANs) recently. However, current inpainting methods are incompetent in handling the cases with large masks and they generally suffer from unreasonable structure. We find that the main reason is the lack of an effective receptive field in the inpainting network. To alleviate this issue, we propose a new two-stage inpainting model called MD-GAN, which is a multi-scale diverse GAN. We inject dense combinations of dilated convolutions in multiple scales of inpainting networks to obtain more effective receptive fields. In fact, the result of inpainting large masks is generally not uniquely deterministic. To this end, we newly propose the multi-scale probabilistic diverse module, which achieves diverse content generation by spatial-adaptive normalization. Meanwhile, the convolutional block attention module is introduced to improve the ability to extract complex features. Perceptual diversity loss is added to enhance diversity. Extensive experiments on benchmark datasets including CelebA-HQ, Places2 and Paris Street View demonstrate that our approach is able to effectively inpaint diverse and structurally reasonable images.