Defining Image Memorability using the Visual Memory Schema
This work addresses the challenge of understanding and predicting image memorability for applications in fields like advertising or education, but it is incremental as it builds upon existing approaches by incorporating human annotations.
The study tackled the problem of predicting image memorability by introducing the Visual Memory Schema (VMS) concept, which organizes image components based on human annotations, and found that adapting deep learning architectures with transfer learning improved the reconstruction and prediction of memorable regions.
Memorability of an image is a characteristic determined by the human observers' ability to remember images they have seen. Yet recent work on image memorability defines it as an intrinsic property that can be obtained independent of the observer. {The current study aims to enhance our understanding and prediction of image memorability, improving upon existing approaches by incorporating the properties of cumulative human annotations.} We propose a new concept called the Visual Memory Schema (VMS) referring to an organisation of image components human observers share when encoding and recognising images. The concept of VMS is operationalised by asking human observers to define memorable regions of images they were asked to remember during an episodic memory test. We then statistically assess the consistency of VMSs across observers for either correctly or incorrectly recognised images. The associations of the VMSs with eye fixations and saliency are analysed separately as well. Lastly, we adapt various deep learning architectures for the reconstruction and prediction of memorable regions in images and analyse the results when using transfer learning at the outputs of different convolutional network layers.