Recent deep learning methods have achieved promising results in image shadow removal.
However, their restored images still suffer from unsatisfactory boundary artifacts, due to the …

Few-shot classification aims to learn a discriminative feature representation to recognize
unseen classes with few labeled support samples. While most few-shot learning methods …

Abstract Model quantization is widely used to compress and accelerate deep neural
networks. However recent studies have revealed the feasibility of weaponizing model …

Deep learning has significantly transformed face recognition, enabling the deployment of
large-scale, state-of-the-art solutions worldwide. However, the widespread adoption of deep …

While raw images exhibit advantages over sRGB images (eg linearity and fine-grained
quantization level), they are not widely used by common users due to the large storage …

Ensuring data privacy and protection has become paramount in the era of deep learning.
Unlearnable examples are proposed to mislead the deep learning models and prevent data …

Abstract Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against
presentation attacks. With advancements in sensor manufacture and multi-modal learning …

As asynchronous event data is more frequently engaged in various vision tasks, the risk of
backdoor attacks becomes more evident. However, research into the potential risk …

Abstract Skeleton Action Recognition (SAR) has attracted significant interest for its efficient
representation of the human skeletal structure. Despite its advancements, recent studies …

In autonomous driving behavior prediction is fundamental for safe motion planning hence
the security and robustness of prediction models against adversarial attacks are of …