Surprising videos, e.g., funny clips, creative performances, or visual
i...
High-quality instructions and responses are essential for the zero-shot
...
Class-Incremental Learning (CIL) or continual learning is a desired
capa...
With the development of deep learning, the field of face anti-spoofing (...
Large language models (LLMs) have demonstrated significant universal
cap...
Large-scale models trained on broad data have recently become the mainst...
The recent success of pre-trained 2D vision models is mostly attributabl...
We present a systematic study of domain generalization (DG) for tiny neu...
Though impressive performance has been achieved in specific visual realm...
The size of vision models has grown exponentially over the last few year...
The field of face anti-spoofing (FAS) has witnessed great progress with ...
Large-scale datasets play a vital role in computer vision. Existing data...
As facial interaction systems are prevalently deployed, security and
rel...
As facial interaction systems are prevalently deployed, security and
rel...