I am currently pursuing a Ph.D. in Electronics and Information - Artificial Intelligence at Nanjing University of Science and Technology（南京理工大学计算机学院）. My current research focuses on talking head generation and editing, as well as audio-based emotion-driven talking head generation. My advisor is Professor Jian Yang (杨健), with Professor Jianjun Qian (钱建军) as my co-advisor. I also collaborate with Associate Professor Zhenyu Zhang (张振宇) from Nanjing University (南京大学) and Assistant Professor Hao Tang (唐浩) from Peking University (北京大学).
If you are interested in our work, feel free to contact me via email at yhjhdu@163.com.
🔥 News
- 2024.07: 🎉🎉 Our paper "ConsistentAvatar" is accepted by ACMMM 2024 (Oral presentation).
📝 Publications
ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidance
Haijie Yang, Zhenyu Zhang*, Hao Tang, Jianjun Qian, Jian Yang*
ConsistentAvatar can generate fully consistent talking head avatars, including temporal consistency, expression consistency, and 3D consistency.