Experiences from the MediaEval Predicting Media Memorability Task

TL;DR

This paper summarizes the MediaEval Predicting Media Memorability task, highlighting its role in benchmarking techniques, refining methods, and providing resources that benefit the broader research community.

Contribution

It provides an overview of the task's evolution, lessons learned, and its impact on advancing media memorability prediction research.

Findings

Benchmarking of multiple memorability prediction techniques.

Development of shared resources for media memorability.

Insights into improving prediction methods.

Abstract

The Predicting Media Memorability task in the MediaEval evaluation campaign has been running annually since 2018 and several different tasks and data sets have been used in this time. This has allowed us to compare the performance of many memorability prediction techniques on the same data and in a reproducible way and to refine and improve on those techniques. The resources created to compute media memorability are now being used by researchers well beyond the actual evaluation campaign. In this paper we present a summary of the task, including the collective lessons we have learned for the research community.