Text-to-image diffusion models are nothing but a revolution, allowing anyone, even without
design skills, to create realistic images from simple text inputs. With powerful personalization …

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an
encoder which can be used as a general-purpose feature extractor, such that downstream …

Multimodal contrastive learning aims to train a general-purpose feature extractor, such as
CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit …

Facial expression recognition (FER) is embedded in many real-world human-computer
interaction tasks, such as online learning, depression recognition and remote diagnosis …

The success of deep learning based face recognition systems has given rise to serious
privacy concerns due to their ability to enable unauthorized tracking of users in the digital …

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible
perturbations to benign examples. The attack transferability enables adversarial examples to …

Traditional personal image privacy protection usually suffers from the overprotection
problem, where one or more undesired persons in an image may be inevitably shielded …

A number of applications (eg, video surveillance and authentication) rely on automated face
recognition to guarantee functioning of secure services, and meanwhile, have to take into …

Increasing numbers of artificial intelligence systems are employing collaborative machine
learning techniques, such as federated learning, to build a shared powerful deep model …

The increasingly pervasive facial recognition (FR) systems raise serious concerns about
personal privacy, especially for billions of users who have publicly shared their photos on …