Video Memorability
Video memorability research aims to understand and predict how well people remember video content, impacting fields like advertising and education. Current research employs machine learning models, including transformer networks and convolutional neural networks, often analyzing visual saliency, temporal patterns (e.g., focusing on initial frames), and even EEG data to identify neural correlates of memorability. These efforts are improving the ability to automatically predict memorability, offering insights into the cognitive processes underlying memory and enabling the creation of more memorable videos.
Papers
Overview of the EEG Pilot Subtask at MediaEval 2021: Predicting Media Memorability
Lorin Sweeney, Ana Matran-Fernandez, Sebastian Halder, Alba G. Seco de Herrera, Alan Smeaton, Graham Healy
Predicting Media Memorability: Comparing Visual, Textual and Auditory Features
Lorin Sweeney, Graham Healy, Alan F. Smeaton