Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation

方法与贡献

FSA-CDM 将细粒度跨模态序列对齐、上下文建模和对比增强的扩散目标结合，用于标记语言到图像生成。

这项后续工作沿用 Deng、Kojima 和 Rush 提出的任务与四个数据集，研究对齐与对比反馈。

结合主题阅读

学习渲染 LaTeX、SMILES、HTML 与乐谱 →

引用

Guojin Zhong, Jin Yuan, Pan Wang, Kailun Yang, Weili Guan, Zhiyong Li. Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation. ACM Multimedia 2023.

@inproceedings{zhong2023contrastaugmented,
  title = {{Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation}},
  author = {Zhong, Guojin and Yuan, Jin and Wang, Pan and Yang, Kailun and Guan, Weili and Li, Zhiyong},
  year = {2023},
  booktitle = {ACM Multimedia 2023},
  url = {https://arxiv.org/abs/2308.01147},
  eprint = {2308.01147},
  archivePrefix = {arXiv}
}