Dynamic User Interface Composition

Abstract

With continuous innovation and a persistent attempt to achieve natural human machine interactions, user interfaces have evolved into the current phase of Voice User Interfaces. Voice User Interfaces augmented with visual information are becoming prominent in a variety of devices with different form-factors. Developing user interfaces for such a wide range of display configurations is a challenging task. This paper puts forward an approach to dynamically compositing such user interfaces without compromising on User Experience. This work examines details of devising a neural network model to automate user interface layout composition based on aesthetics and saliency. A 40000 dataset was created for this work with eight trained annotators. Ground truth is estimated from the above annotations using Expectation Maximization algorithm. Experiments show that users are highly satisfied with the model results. This model is deployed in Lock Screen auto layout available in latest Samsung Android phones.