Conversational Content Acquisition by Ubiquitous Sensors
Yasuyuki Sumi, Kenji Mase, Toyoaki Nishida · 2007
This chapter contains sections titled: Introduction Capturing Conversation Scenes by Multiple Sensors Segmentation and Interpretation of Scenes Video Summary: Chronological Collage of Multiple-viewpoint Videos Building 3D Virtual Space by Spatiotemporal Video Collage The Ambient Sound Shower: Sound Collage for Revealing Situated Conversations Inferring Semantic Information about Detected Conversation Scenes by Nonverbal Information Related Work Conclusions References