Visual memorability is a method to measure how easily media contents can be memorized. Predicting the visual memorability of media contents has recently become more important because it can affect the design principles of multimedia visualization, advertisement, etc. Previous studies on the prediction of the visual memorability of images generally exploited visual features (e.g., color intensity and contrast) or semantic information (e.g., class labels) that can be extracted from images. Some other works tried to exploit electroencephalography (EEG) signals of human subjects to predict the memorability of text (e.g., word pairs). Compared to previous works, we focus on predicting the visual memorability of images based on human biological feedback (i.e., EEG signals). For this, we design a visual memory task where each subject is asked to answer whether they correctly remember a particular image 30 min after glancing at a set of images sampled from the LaMemdataset. During the visual memory task, EEG signals are recorded from subjects as human biological feedback. The collected EEG signals are then used to train various classification models for prediction of image memorability. Finally, we evaluate and compare the performance of classification models, including deep convolutional neural networks and classical methods, such as support vector machines, decision trees, and k-nearest neighbors. The experimental results validate that the EEG-based prediction of memorability is still challenging, but a promising approach with various opportunities and potentials.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited