본문 바로가기
  • Home

Design and Evaluation of Video Summarization Algorithm based on EEG Information

Kim, Hyun Hee 1 Yong-Ho Kim 2

1명지대학교
2부경대학교

Excellent Accredited

ABSTRACT

We proposed a video summarization algorithm based on an ERP (Event Related Potentials)-based topic relevance model, a MMR (Maximal Marginal Relevance), and discriminant analysis to generate a semantically meaningful video skim. We then conducted implicit and explicit evaluations to evaluate our proposed ERP/MMR-based method. The results showed that in the implicit and explicit evaluations, the average scores of the ERP / MMR methods were statistically higher than the average score of the SBD (Shot Boundary Detection) method used as a competitive baseline, respectively. However, there was no statistically significant difference between the average score of ERP/MMR (λ = 0.6) method and that of ERP/MMR (λ = 1.0) method in both assessments.

Citation status

* References for papers published after 2022 are currently being built.

This paper was written with support from the National Research Foundation of Korea.