English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The appearances of children are inherited from their parents, which makes itfeasible to predict them. Predicting realistic children's faces may help settlemany social problems, such as age-invariant face recognition, kinshipverification, and missing child identification. It can be regarded as animage-to-image translation task. Existing approaches usually assume domaininformation in the image-to-image translation can be interpreted by "style",i.e., the separation of image content and style. However, such separation isimproper for the child face prediction, because the facial contours betweenchildren and parents are not the same. To address this issue, we propose a newdisentangled learning strategy for children's face prediction. We assume thatchildren's faces are determined by genetic factors (compact family features,e.g., face contour), external factors (facial attributes irrelevant toprediction, such as moustaches and glasses), and variety factors (individualproperties for each child). On this basis, we formulate predictions as amapping from parents' genetic factors to children's genetic factors, anddisentangle them from external and variety factors. In order to obtain accurategenetic factors and perform the mapping, we propose a ChildPredictor framework.It transfers human faces to genetic factors by encoders and back by generators.Then, it learns the relationship between the genetic factors of parents andchildren through a mapping function. To ensure the generated faces arerealistic, we collect a large Family Face Database to train ChildPredictor andevaluate it on the FF-Database validation set. Experimental results demonstratethat ChildPredictor is superior to other well-known image-to-image translationmethods in predicting realistic and diverse child faces. Implementation codescan be found at https://github.com/zhaoyuzhi/ChildPredictor.

ChildPredictor: A Child Face Prediction Framework with Disentangled Learning