This paper describes our approach designed for the MediaEval 2018 Predicting Media Memorability Task. First, a subspace learning method called Memorability Preserving Embedding (MPE) is proposed to learn discriminative subspace from the original feature space according to the memorability scores. Then the Support Vector Regressor (SVR) is applied to the learned subspace for memorability prediction. The prediction performance demonstrates that SVR can achieve good performance even in a very low-dimensional subspace, which implies that the subspace learned by the MPE is capable of preserving important memorability information. Moreover, the results indicate that the short-term memorability is more predictable than the long-term memorability. Copyright held by the owner/author(s).
|Journal||CEUR Workshop Proceedings|
|Publication status||Published - 2018|
|Event||2018 Working Notes Proceedings of the MediaEval Workshop, MediaEval 2018 - Sophia Antipolis, France|
Duration: 29 Oct 2018 → 31 Oct 2018
Scopus Subject Areas
- Computer Science(all)