no code implementations • 28 May 2024 • Zebin You, Xinyu Zhang, Hanzhong Guo, Jingdong Wang, Chongxuan Li
The ultimate goal of generative models is to characterize the data distribution perfectly.
no code implementations • 23 May 2024 • Yong Zhong, Min Zhao, Zebin You, Xiaofeng Yu, Changwang Zhang, Chongxuan Li
In this paper, we introduce PoseCrafter, a one-shot method for personalized video generation following the control of flexible poses.
2 code implementations • NeurIPS 2023 • Zebin You, Yong Zhong, Fan Bao, Jiacheng Sun, Chongxuan Li, Jun Zhu
In an effort to further advance semi-supervised generative and classification tasks, we propose a simple yet effective training strategy called dual pseudo training (DPT), built upon strong semi-supervised learners and diffusion models.