What makes an image memorable?

Phillip Isola, Jianxiong Xiao, Antonio Torralba, Aude Oliva



Abstract

When glancing at a magazine, or browsing the Internet, we are continuously being 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 stitch to our minds, and other are forgotten. In this paper we focus on the problem of predicting how memorable an image will be. We show that memorability is a stable property of an image that is shared across different viewers. We introduce a database for which we have measured the probability that each picture will be remembered after a single view. We analyze image features and labels 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. Whereas making memorable images is a challenging task in visualization and photography, this work is a first attempt to quantify this useful quality of images.

Paper

Isola, P., Xiao, J., Torralba, A., Oliva, A. What makes an image memorable? IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. Pages 145-152.

Poster

CVPR 2011

Code and data

Image memorability dataset. Includes target and filler images, precomputed features and annotations, and memorability measurements from our "Memory Game".

Code. Code for computing features of new images, predicting their memorability, and replicating our results.

Bibtex

@inproceedings{Isola2011,
   author="Phillip Isola and Jianxiong Xiao and Antonio Torralba and Aude Oliva", 
   title="What makes an image memorable?", 
   booktitle="IEEE Conference on Computer Vision and Pattern Recognition (CVPR)", 
   year="2011",
   pages="145-152"
}

Acknowledgments

We would like to thank Timothy Brady and Talia Konkle for helpful discussions and advice. This work is supported by the National Science Foundation under Grant No. 1016862 to A.O, CAREER Awards No. 0546262 to A.O and No. 0747120 to A.T. A.T. was supported in part by the Intelligence Advanced Research Projects Activity via Department of the Interior contract D10PC20023, and ONR MURI N000141010933.