Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Predicting media memorability using ensemble models
Azcona, David; Moreu, Enric; Hu, Feiyan; Ward, Tomás E.; Smeaton, Alan F.
Memorability, defined as the quality of being worth remembering, is a pressing issue in media as we struggle to organize and retrieve digital content and make it more useful in our daily lives. The Predicting Media Memorability task in MediaEval 2019 tackles this problem by creating a challenge to automatically predict memorability scores building on the work developed in 2018. Our team ensembled transfer learning approaches with video captions using embeddings and our own pre-computed features which outperformed Medieval 2018’s state-of-the-art architectures.
Keyword(s): Machine learning
Publication Date:
2020
Type: Other
Peer-Reviewed: Unknown
Language(s): English
Institution: Dublin City University
Citation(s): Azcona, David ORCID: 0000-0003-3693-7906 <https://orcid.org/0000-0003-3693-7906>, Moreu, Enric, Hu, Feiyan ORCID: 0000-0001-7451-6438 <https://orcid.org/0000-0001-7451-6438>, Ward, Tomás E. ORCID: 0000-0002-6173-6607 <https://orcid.org/0000-0002-6173-6607> and Smeaton, Alan F. ORCID: 0000-0003-1028-8389 <https://orcid.org/0000-0003-1028-8389> (2020) Predicting media memorability using ensemble models. In: MediaEval 2019, 27 - 29 Oct 2019, Sophia Antipolis, France.
Publisher(s): CEUR Workshop Proceedings
File Format(s): application/pdf
Related Link(s): http://doras.dcu.ie/23833/1/David_Azcona_MediaEval_2019_Memorability_Camera_ready.pdf,
http://ceur-ws.org/Vol-2670/
First Indexed: 2019-10-26 07:14:21 Last Updated: 2020-09-24 06:29:40