Age progression/regression is a challenging task due to the complicated and non-linear
transformation in human aging process. Many researches have shown that both global and …

Age synthesis is a challenging task due to the complicated and non-linear transformation in
the human aging process. Aging information is usually reflected in local facial parts, such as …

Super-resolution (SR) is able to improve the spatial resolution of remote sensing images,
which is critical for many practical applications such as fine urban monitoring. In this paper, a …

Deep neural networks have become the dominant paradigm for artificial intelligence (AI) in
the past decade, and deep learning has significantly advanced various areas of AI …

Face completion aims to generate semantically new pixels for missing facial components. It
is a challenging generative task due to large variations of face appearance. This paper …

Facial expression synthesis with various intensities is a challenging synthesis task due to
large identity appearance variations and a paucity of efficient means for intensity …

Activity recognition is essential in computer vision applications such as smart homes and
healthcare services. While RGB images have been widely used in this area, they pose …

ID face photos are widely used for identity verification in many business authentication
situations. To avoid any infringement and misuse, the ID photos provided by the relevant …

Majority of face recognition systems can only retrieve protected ID photos from the
government agency in China. These facial images covered with mesh-like curves are …

In this chapter, we introduce dual learning for unsupervised image to image translation. We
first introduce several representative and contemporary algorithms for image translation in …