Addressee detection using facial and audio features in mixed human–human and human–robot settings: a deep learning framework

Keyphrases

• Addressee Detection 100%
• Annotated Dataset 50%
• Audio Features 100%
• Audio Information 50%
• Deep Learning Framework 100%
• Facial Features 100%
• Human-to-human 100%
• Meeting Room 50%
• Rule-based Approach 50%
• Spatiotemporal 50%
• Specific Settings 50%
• Statistical Methods 50%
• Utterance 50%
• Visual Information 50%

Computer Science

• Deep Learning 100%
• Learning Framework 100%
• Robot 100%
• Visual Informations 33%