en
Proceedings chapter
Open access
English

Spectators' Synchronization Detection based on Manifold Representation of Physiological Signals: Application to Movie Highlights Detection

Presented at Seattle, USA, November 09 - 13, 2015
Publication date2015
Abstract

Detection of highlights in movies is a challenge for the affective understanding and implicit tagging of films. Under the hypothesis that synchronization of the reaction of spectators indicates such highlights, we define a synchronization measure between spectators that is capable of extracting movie highlights. The intuitive idea of our approach is to define (a) a parameterization of one spectator's physiological data on a manifold; (b) the synchronization measure between spectators as the Kolmogorov-Smirnov distance between local shape distributions of the underlying manifolds. We evaluate our approach using data collected in an experiment where the electro-dermal activity of spectators was recorded during the entire projection of a movie in a cinema. We compare our methodology with baseline synchronization measures, such as correlation, Spearman's rank correlation, mutual information, Kolmogorov-Smirnov distance. Results indicate that the proposed approach allows to accurately distinguish highlight from non-highlight scenes.

Keywords
  • Synchronization
  • Physiological Signals
  • Affective Computing
  • Time Delay Embedding
  • Manifold Learning
  • Dimensionality Reduction
  • Diffusion Maps
  • Highlights Detection
Citation (ISO format)
MUSZYNSKI, Michal et al. Spectators” Synchronization Detection based on Manifold Representation of Physiological Signals: Application to Movie Highlights Detection. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction. Seattle, USA. [s.l.] : [s.n.], 2015. doi: 10.1145/2818346.2820773
Main files (1)
Proceedings chapter (Accepted version)
accessLevelPublic
Identifiers
ISBN978-1-4503-3912-4
808views
305downloads

Technical informations

Creation11/29/2015 9:54:00 PM
First validation11/29/2015 9:54:00 PM
Update time03/14/2023 11:56:28 PM
Status update03/14/2023 11:56:28 PM
Last indexation01/16/2024 7:45:05 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack