A5101649664- Face recognition and analysis
- Digital Media Forensic Detection
- Adversarial Robustness in Machine Learning
- Video Analysis and Summarization
- Speech and Audio Processing
- Generative Adversarial Networks and Image Synthesis
University of Chinese Academy of Sciences
2023-2024
Institute of Automation
2024
Talking-head video editing aims to efficiently insert, delete, and substitute the word of a pre-recorded through text transcript editor. The key challenge for this task is obtaining an model that generates new talking-head clips which simultaneously have accurate lip synchronization motion smoothness. Previous approaches, including 3DMM-based (3D Morphable Model) methods NeRF-based (Neural Radiance Field) methods, are sub-optimal in they either require minutes source videos days training...
Deep neural networks have enhanced face synthesis detection in discriminating Artificial Intelligence Generated Content (AIGC). However, their security is threatened by the injection of carefully crafted triggers during model training (i.e., backdoor attacks). Although existing defenses and manual data selection are able to mitigate those using human-eye-sensitive triggers, such as patches or adversarial noises, more challenging natural remain insufficiently researched. To further...