Memorability: An image-computable measure of information utility

TL;DR

This paper reviews computational methods for predicting and manipulating image memorability, highlighting deep learning approaches and their applications in visual filtering and augmented reality.

Contribution

It provides a comprehensive overview of state-of-the-art algorithms for image memorability prediction and discusses recent AI techniques for creating and modifying memorability.

Findings

Deep learning models accurately predict image memorability.

Algorithms generalize to actions and videos.

AI can modify visual memorability for applications.

Abstract

The pixels in an image, and the objects, scenes, and actions that they compose, determine whether an image will be memorable or forgettable. While memorability varies by image, it is largely independent of an individual observer. Observer independence is what makes memorability an image-computable measure of information, and eligible for automatic prediction. In this chapter, we zoom into memorability with a computational lens, detailing the state-of-the-art algorithms that accurately predict image memorability relative to human behavioral data, using image features at different scales from raw pixels to semantic labels. We discuss the design of algorithms and visualizations for face, object, and scene memorability, as well as algorithms that generalize beyond static scenes to actions and videos. We cover the state-of-the-art deep learning approaches that are the current front runners in the memorability prediction space. Beyond prediction, we show how recent A.I. approaches can be used to create and modify visual memorability. Finally, we preview the computational applications that memorability can power, from filtering visual streams to enhancing augmented reality interfaces.