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 …
X Chen, X Zheng, K Sun, W Liu, Y Zhang - Information Sciences, 2023 - Elsevier
Facial expression recognition (FER) is embedded in many real-world human-computer interaction tasks, such as online learning, depression recognition and remote diagnosis …
F Shamshad, M Naseer… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …
K Liang, B Xiao - Proceedings of the IEEE/CVF Conference …, 2023 - openaccess.thecvf.com
Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible perturbations to benign examples. The attack transferability enables adversarial examples to …
J Lin, X Dai, K Nai, J Yuan, Z Li, X Zhang, S Li - Expert Systems with …, 2023 - Elsevier
Traditional personal image privacy protection usually suffers from the overprotection problem, where one or more undesired persons in an image may be inevitably shielded …
L Yuan, L Liu, X Pu, Z Li, H Li, X Gao - Proceedings of the 30th ACM …, 2022 - dl.acm.org
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 …
F Yang, X Zhang, S Guo, D Chen, Y Gan… - Artificial Intelligence …, 2024 - Springer
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 …