自编码
面子(社会学概念)
计算机科学
特征(语言学)
一致性(知识库)
人工智能
编码器
健康衰老
代表(政治)
特征学习
模式识别(心理学)
深度学习
政治
操作系统
老年学
哲学
社会学
医学
法学
语言学
社会科学
政治学
作者
Lipeng Lu,Shenghui Wang,Lei Wan,Haibo Yu
标识
DOI:10.1016/j.jvcir.2022.103452
摘要
Existing face aging (FA) approaches usually concentrate on a universal aging pattern, and produce restricted aging faces from one-to-one mapping. However, the diversity of living environments impact individuals differently in their oldness. To simulate various aging effects, we propose a multimodal FA framework based on face disentanglement technique of age-specific and age-irrelevant information. A Variational Autoencoder (VAE)-based encoder is designed to represent the distribution of the age-specific attributes. To capture the age-irrelevant features, a cycle-consistency loss of unpaired faces is utilized among various age spans. The extensive experimental results demonstrate that the sampled age-specific codes along with an age-irrelevant feature make the multimodal FA diverse and realistic.
科研通智能强力驱动
Strongly Powered by AbleSci AI