What Makes a Photograph Memorable?

By Phillip Isola, Jianxiong Xiao, Devi Parikh, Antonio Torralba, Aude Oliva. 2014

292 citations recorded by the source corpus.

When glancing at a magazine, or browsing the Internet, we are continuously exposed to photographs. Despite this overflow of visual information, humans are extremely good at remembering thousands of pictures along with some of their visual details. But not all images are equal in memory. Some stick in our minds while others are quickly forgotten. In this paper, we focus on the problem of predicting how memorable an image will be. We show that memorability is an intrinsic and stable property of an image that is shared across different viewers, and remains stable across delays. We introduce a database for which we have measured the probability that each picture will be recognized after a single view. We analyze a collection of image features, labels, and attributes that contribute to making an image memorable, and we train a predictor based on global image descriptors. We find that predicting image memorability is a task that can be addressed with current computer vision techniques. While making memorable images is a challenging task in visualization, photography, and education, this work is a first attempt to quantify this useful property of images.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Neuroaesthetics in fashion: Modeling the perception of fashionability (2015, background): “In [5, 7, 10, 15] the authors addressed the question of what makes an image memorable, interesting or popular.”
Becoming the expert - interactive multi-class machine teaching (2015, background): “Some images are intrinsically more ‘memorable’ than others [12, 20], and incorporating such measures into teaching image selection may also improve test time performance.”
Deep Neural Networks Predict Category Typicality Ratings for Images (2015, background): “One study by Isola, Xiao, Parikh, Torralba, and Oliva (2013) showed that image memorability (which is not necessarily analogous to typicality) could be predicted from raw images with a rank correlation of ρ = 0 .”
Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text (2018, unknown): “Some study the memorability of images [15, 19].”
Understanding and Predicting Image Memorability at a Large Scale (2015, methodology): “This procedure is based on the finding that the memorability ranks of images are time-independent [13].”
Beyond Memorability: Visualization Recognition and Recall (2016, background): “Memorability has been demonstrated to be an intrinsic property of scene images [12, 23], faces [3], and graphs [8].”
STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset (2017, unknown): “C L ] 2 M ay 2 01 7 2015; Isola et al., 2014).”
GANalyze: Toward Visual Definitions of Cognitive Image Properties (2019, methodology): “Why do we remember the things we do? Decades of work have provided numerous explanations: we remember things that are out of context [5, 30], that are emotionally salient [4], that involve people [14], etc.”