papers AI Learner
The Github is limit! Click to go to the new site.

Is Image Memorability Prediction Solved?

2019-01-31
Shay Perera, Ayellet Tal, Lihi Zelnik-Manor

Abstract

This paper deals with the prediction of the memorability of a given image. We start by proposing an algorithm that reaches human-level performance on the LaMem dataset - the only large scale benchmark for memorability prediction. The suggested algorithm is based on three observations we make regarding convolutional neural networks (CNNs) that affect memorability prediction. Having reached human-level performance we were humbled, and asked ourselves whether indeed we have resolved memorability prediction - and answered this question in the negative. We studied a few factors and made some recommendations that should be taken into account when designing the next benchmark.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.11420

PDF

http://arxiv.org/pdf/1901.11420


Similar Posts

Comments