Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

Qiucheng Wu, Yujian Liu, Handong Zhao, Trung Bui, Zhe Lin, Yang Zhang, Shiyu Chang. Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. pages 7732-7742, IEEE, 2023. [doi]

@inproceedings{WuLZBLZC23,
  title = {Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis},
  author = {Qiucheng Wu and Yujian Liu and Handong Zhao and Trung Bui and Zhe Lin and Yang Zhang and Shiyu Chang},
  year = {2023},
  doi = {10.1109/ICCV51070.2023.00714},
  url = {https://doi.org/10.1109/ICCV51070.2023.00714},
  researchr = {https://researchr.org/publication/WuLZBLZC23},
  cites = {0},
  citedby = {0},
  pages = {7732-7742},
  booktitle = {IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023},
  publisher = {IEEE},
  isbn = {979-8-3503-0718-4},
}