Is Image Memorability Prediction Solved?
This work addresses the challenge of predicting image memorability for computer vision applications, but it is incremental as it builds on existing datasets and methods.
The authors tackled image memorability prediction by proposing an algorithm that achieves human-level performance on the LaMem dataset, but they concluded that the problem is not fully solved and provided recommendations for future benchmarks.
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.