Skip to main content
DORAS
DCU Online Research Access Service
Login (DCU Staff Only)
Overview of The MediaEval 2021 Predicting Media Memorability Task

Kiziltepe, Rukiye Savran ORCID: 0000-0002-3862-7621, Constantin, Mihai Gabriel ORCID: 0000-0002-2312-6672, Demarty, Claire-Hélène, Healy, Graham ORCID: 0000-0001-6429-6339, Fosco, Camilo, García Seco de Herrera, Alba ORCID: 0000-0002-6509-5325, Halder, Sebastian ORCID: 0000-0003-1017-3696, Ionescu, Bogdan, Matran-Fernandez, Ana ORCID: 0000-0002-8409-3747, Smeaton, Alan F. ORCID: 0000-0003-1028-8389 and Sweeney, Lorin ORCID: 0000-0002-3427-1250 (2021) Overview of The MediaEval 2021 Predicting Media Memorability Task. In: MediaEval: MediaEval Benchmarking Initiative for Multimedia Evaluation, 2021, 13-15 Dec 2021, Online.

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
365kB

Abstract

This paper describes the MediaEval 2021 Predicting Media Memorability}task, which is in its 4th edition this year, as the prediction of short-term and long-term video memorability remains a challenging task. In 2021, two datasets of videos are used: first, a subset of the TRECVid 2019 Video-to-Text dataset; second, the Memento10K dataset in order to provide opportunities to explore cross-dataset generalisation. In addition, an Electroencephalography (EEG)-based prediction pilot subtask is introduced. In this paper, we outline the main aspects of the task and describe the datasets, evaluation metrics, and requirements for participants' submissions.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Subjects:Computer Science > Artificial intelligence
Computer Science > Machine learning
Computer Science > Multimedia systems
Computer Science > Digital video
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Published in: Working Notes Proceedings of the MediaEval 2021 Workshop. . CEUR-WS.
Publisher:CEUR-WS
Official URL:https://2021.multimediaeval.com/
Copyright Information:© 2021 The Authors. Open Access (CC-BY-4.0)
Funders:Science Foundation Ireland grant number SFI/12/RC/2289_P2., H2020 ICT-48-2020, grant 951911 AI4Media, NIST Award No. 60NANB19D155, Turkish Ministry of National Education
ID Code:26533
Deposited On:13 Dec 2021 14:01 by Alan Smeaton . Last Modified 27 Jul 2022 10:14

Downloads

Downloads per month over past year

Archive Staff Only: edit this record

  • Student Email
  • Staff Email
  • Student Apps
  • Staff Apps
  • Loop
  • Disclaimer
  • Privacy
  • Contact Us