Our paper on "Experiences from the MediaEval Predicting Media Memorability Task" by Alba G. Seco de Herrera, Mihai Gabriel Constantin, Claire-Hélène Demarty, Camilo Fosco, Sebastian Halder, Graham Healy, Bogdan Ionescu, Ana Matran-Fernandez, Alan F. Smeaton, Mushfika Sultana and Lorin Sweeney has been accepted at the Memory in Artificial and Real Intelligence (MemARI) NeurIPS 2022 workshop.
The Predicting Media Memorability task in the MediaEval evaluation campaign
2 has been running annually since 2018 and several different tasks and data sets have
3 been used in this time. This has allowed us to compare the performance of many
4 memorability prediction techniques on the same data and in a reproducible way and
5 to refine and improve on those techniques. The resources created to compute media
6 memorability are now being used by researchers well beyond the actual evaluation
7 campaign. In this paper we present a summary of the evaluation campaign including
8 the collective lessons we have learned for the research community.
