Siyuan Wang
Research Subjects
Siyuan Wang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Kaizhu Huang
Duke Kunshan University, Kunshan, China
3 shared publications - Xi Yang
Xi’an Jiaotong-Liverpool University, Suzhou, China
2 shared publications - Erik Cambria
Nanyang technological university, Singapore, Singapore
1 shared publication Guangliang Cheng
1 shared publication- Jing Li
College of Science & Technology, Ningbo University, Ningbo 315300, China
1 shared publication Qiufeng Wang
1 shared publication
Latest Publications
- Open Access
- 21 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (6) , 1-24
Diff-Oracle: Learning Styles and Contents to Augment Realistic Oracle Characters in Diffusion Model
Recognizing oracle bone scripts plays an important role in Chinese archaeology and philology. However, a significant challenge remains because of the scarcity of oracle character images. To overcome this issue, we propose Diff-Oracle, a novel multi-modal conditional diffusion model that generates a diverse range of controllable oracle characters by inputting random combinations of references. Given the challenge of accurately describing oracle character styles using natural language, Diff-Oracle departs from traditional diffusion models that rely primarily on text prompts by introducing a style encoder. This encoder extracts style prompts from existing oracle character images, where style details are converted into a text embedding format via a pre-trained language-vision model. Additionally, given the lack of explicit content information for oracle characters, ensuring that generated characters accurately represent the intended glyphs is challenging. Therefore, we pre-generate pixel-level paired oracle character images (i.e., style and content images) by an image-to-image translation model, providing content information for the generation process. Meanwhile, Diff-Oracle integrates a content encoder designed to capture specific content details from content reference images. Extensive experiments on Oracle-241 and OBC306 datasets demonstrate that Diff-Oracle significantly outperforms existing generative methods in image quality and diversity. Moreover, Diff-Oracle substantially benefits downstream recognition tasks, outperforming all existing state-of-the-art methods by a large margin. In particular, on the challenging OBC306 dataset, Diff-Oracle achieves a 7.70% accuracy gain in the zero-shot setting and reaches 84.62% accuracy for unseen oracle characters, setting a new benchmark for oracle character recognition. The code is available at https://github.com/JJJingLi/Diff-Oracle .
- 21 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (6) , 1-24
Open AccessDiff-Oracle: Learning Styles and Contents to Augment Realistic Oracle Characters in Diffusion Model
Recognizing oracle bone scripts plays an important role in Chinese archaeology and philology. However, a significant challenge remains because of the scarcity of oracle character images. To overcome this issue, we propose Diff-Oracle, a novel multi-modal conditional diffusion model that generates a diverse range of controllable oracle characters by inputting random combinations of references. Given the challenge of accurately describing oracle character styles using natural language, Diff-Oracle departs from traditional diffusion models that rely primarily on text prompts by introducing a style encoder. This encoder extracts style prompts from existing oracle character images, where style details are converted into a text embedding format via a pre-trained language-vision model. Additionally, given the lack of explicit content information for oracle characters, ensuring that generated characters accurately represent the intended glyphs is challenging. Therefore, we pre-generate pixel-level paired oracle character images (i.e., style and content images) by an image-to-image translation model, providing content information for the generation process. Meanwhile, Diff-Oracle integrates a content encoder designed to capture specific content details from content reference images. Extensive experiments on Oracle-241 and OBC306 datasets demonstrate that Diff-Oracle significantly outperforms existing generative methods in image quality and diversity. Moreover, Diff-Oracle substantially benefits downstream recognition tasks, outperforming all existing state-of-the-art methods by a large margin. In particular, on the challenging OBC306 dataset, Diff-Oracle achieves a 7.70% accuracy gain in the zero-shot setting and reaches 84.62% accuracy for unseen oracle characters, setting a new benchmark for oracle character recognition. The code is available at https://github.com/JJJingLi/Diff-Oracle .
- 4 July 2025
- Published by Elsevier in Pattern Recognition
- Vol. 170
Point2pix-Zero: Point-driven refined diffusion for multi-object image editing
- 4 July 2025
- Published by Elsevier in Pattern Recognition
- Vol. 170
Point2pix-Zero: Point-driven refined diffusion for multi-object image editing
- 24 June 2025
- Published by Springer Nature
- p. 196-210
Enhancing Semantic Segmentation in Open Compound Domain Adaptation Through Mixed Image and Epistemic Uncertainty
- 24 June 2025
- Published by Springer Nature
- p. 196-210
Enhancing Semantic Segmentation in Open Compound Domain Adaptation Through Mixed Image and Epistemic Uncertainty
- 15 November 2023
- Published by Springer Nature
- p. 433-444
PAG: Protecting Artworks from Personalizing Image Generative Models
- 15 November 2023
- Published by Springer Nature
- p. 433-444
PAG: Protecting Artworks from Personalizing Image Generative Models