Analysis of scene context related with emotional events

  • Authors:

  • Hang-Bong Kang

  • Affiliations:

  • The Catholic University of Korea #43-1 Yokkok 2-Dong Wonmi-Gu, Puchon City, Kyonggi-Do, Korea

  • Venue:
  • Proceedings of the tenth ACM international conference on Multimedia
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose a method for the detection of emotional events by analyzing scene context in video data. To analyze scene-level features, we compute the contextual information in video scenes. We divide the scene context into intra-scene context and interscene context. We define intra-scene context as the context within the scene such as the shots' coherences, shot's interactions and dominant features in color and motion information within the scene. We also define the inter-scene context as the given scene's relationship with other scenes. In detecting emotional events from video data, we first compute inter-scene context. Then, we select possible candidates which have large dissimilarities in comparison with previous scenes. Finally, we make a decision whether the candidate is emotional event or not. We experiment our proposed approach on test data and detect 70% of the occurrences of the emotional events such as fear and sadness.