Self-supervised methods have shown remarkable progress in learning high-...
Cross-modality medical image synthesis is a critical topic and has the
p...
Animating virtual avatars with free-view control is crucial for various
...
Animating virtual avatars to make co-speech gestures facilitates various...
Data-free knowledge distillation is a challenging model lightweight task...
Co-speech gesture is crucial for human-machine interaction and digital
e...
In this paper, we propose a novel learning scheme for self-supervised vi...
The neural implicit representation has shown its effectiveness in novel ...
Generating speech-consistent body and gesture movements is a long-standi...
The task of audio-visual sound source localization has been well studied...
Animating high-fidelity video portrait with speech audio is crucial for
...
The crux of self-supervised video representation learning is to build ge...
Recent advances in image-based human pose estimation make it possible to...