Overview of The MediaEval 2022 Predicting Video Memorability Task

TL;DR

This paper presents the 5th edition of the MediaEval Predicting Video Memorability Task, introducing new datasets, a focus on short-term memorability, and an EEG-based prediction sub-task to advance research in video memorability prediction.

Contribution

The paper introduces updated datasets, simplifies the task structure, and adds an EEG-based sub-task to enhance research on video memorability prediction.

Findings

Replaced TRECVid2019 dataset with VideoMem for better data quality

Elevated Memento10k as primary dataset for short-term memorability

Introduced EEG-based prediction sub-task

Abstract

This paper describes the 5th edition of the Predicting Video Memorability Task as part of MediaEval2022. This year we have reorganised and simplified the task in order to lubricate a greater depth of inquiry. Similar to last year, two datasets are provided in order to facilitate generalisation, however, this year we have replaced the TRECVid2019 Video-to-Text dataset with the VideoMem dataset in order to remedy underlying data quality issues, and to prioritise short-term memorability prediction by elevating the Memento10k dataset as the primary dataset. Additionally, a fully fledged electroencephalography (EEG)-based prediction sub-task is introduced. In this paper, we outline the core facets of the task and its constituent sub-tasks; describing the datasets, evaluation metrics, and requirements for participant submissions.