As deep neural networks (DNNs) are widely applied in the physical world, many researches
are focusing on physical-world adversarial examples (PAEs), which introduce perturbations …

With the rapid advancement of deep learning, the model robustness has become a
significant research hotspot,\ie, adversarial attacks on deep neural networks. Existing works …

No-Reference Image Quality Assessment (NR-IQA), responsible for assessing the quality of
a single input image without using any reference, plays a critical role in evaluating and …

Weakly-supervised segmentation (WSS) has emerged as a solution to mitigate the conflict
between annotation cost and model performance by adopting sparse annotation formats …

Robotic manipulation in the physical world is increasingly empowered by\textit {large
language models}(LLMs) and\textit {vision-language models}(VLMs), leveraging their …

Convolution-based unlearnable examples (UEs) employ class-wise multiplicative
convolutional noise to training samples, severely compromising model performance. This …

Robotic manipulation refers to the autonomous handling and interaction of robots with
objects using advanced techniques in robotics and artificial intelligence. The advent of …