Overview of MediaEval 2020 Predicting Media Memorability Task: What Makes a Video Memorable?

TL;DR

This paper overviews the MediaEval 2020 Predicting Media Memorability task, focusing on short-term and long-term video memorability prediction using a dataset of action-rich videos, and discusses evaluation methods and participant submissions.

Contribution

It provides a detailed description of the 2020 task setup, dataset, evaluation metrics, and the challenge of predicting video memorability, building on previous editions.

Findings

Use of TRECVid 2019 dataset with action-rich videos

Evaluation of memorability prediction methods

Insights into the challenge of short-term and long-term memorability prediction

Abstract

This paper describes the MediaEval 2020 \textit{Predicting Media Memorability} task. After first being proposed at MediaEval 2018, the Predicting Media Memorability task is in its 3rd edition this year, as the prediction of short-term and long-term video memorability (VM) remains a challenging task. In 2020, the format remained the same as in previous editions. This year the videos are a subset of the TRECVid 2019 Video-to-Text dataset, containing more action rich video content as compared with the 2019 task. In this paper a description of some aspects of this task is provided, including its main characteristics, a description of the collection, the ground truth dataset, evaluation metrics and the requirements for participants' run submissions.