Exploiting Facial Expressions for Affective Video Summarisation

This paper presents an approach to affective video summarization based on the facial expressions (FX) of viewers. A facial expression recognition system was deployed to capture a viewer's face and his/her expressions. The user's facial expressions were analyzed to infer personalized affective scenes from videos. We proposed two models, pronounced level and expression's change rate, to generate affective summaries using the FX data. Our result suggested that FX can be a promising source to exploit for affective video summaries that can be tailored to individual preferences.

• Type: Conference
• Year: 2009
• Where: CIVR
• Authors: Hideo Joho, Joemon M. Jose, Roberto Valenti, Nicu Sebe
• Keywords: Affective Video Summarisation, Facial Expression Recognition, Multimedia