AFFECTIVE MEETING VIDEO ANALYSIS (WedPmPO1)

Author(s) : Alejandro Jaimes (FX Pal Japan, Fuji Xerox Co., Ltd., Japan) Takeshi Nagamine (FX Pal Japan, Fuji Xerox Co., Ltd., Japan) Jianyi Liu (FX Pal Japan, Fuji Xerox Co., Ltd., Japan) Kengo Omura (FX Pal Japan, Fuji Xerox Co., Ltd., Japan) Nicu Sebe (University of Amsterdam, Netherlands)

Abstract : In this paper we examine the affective content of meeting videos. First we ask users to manually label meeting videos using continuous response measurement (continuous-scale labeling in real-time) for energy and valence (the two dimensions of the human affect space). Then we automatically extract audio-visual features to characterize the affective content of the meeting. We show the results of plotting both manual and automatic labeling and examine how this kind of information can be used for indexing meeting videos. Our analysis yields promising results, which suggest that affective meeting video analysis can lead to very interesting observations useful for automatic indexing.

Menu