Topics include:

• Multimodal signal and interaction processing technologies:
  Methods for machine learning, data mining, and adaptation for multimodal signals; multimodal signal processing, inference, and input fusion over combinations of signals (e.g., derived from visual, audio, haptic, bio- and machine sensors), semantic interpretations (e.g., of spoken language, gesture, facial expression, sketch), and hybrid combinations; multimodal output planning and coordination (e.g., coordinated speech and gesture); etc.
• Multimodal models for human-human and human-machine interaction:
  Multimodal models for human-human communication dynamics and collaboration, including verbal and non-verbal interaction; models for physically situated human-computer and human-robot interaction; models for multiparty, group and social interaction; models for multimodal dialogue; models for long-term multimodal interaction; affective computing and interaction models; cognitive, linguistic, psycho-linguistic, cultural models, and other perspectives on multimodal interaction and communication; etc..
• Multimodal data, evaluation and tools:
  Multimodal corpora, resources and tools; evaluation methodologies, assessment and metrics; multimodal annotation methodologies and coding schemes; design issues, principles and best practices for multimodal interfaces; authoring techniques; standards; etc.
• Multimodal systems and applications:
  Ambient intelligence and smart environments; human-robot interaction; embodied conversational agents; multimodal interfaces for internet-of-things; multimodal automotive user interfaces; virtual and augmented reality; meeting spaces and meeting analysis systems; multimodal mobile applications; education; entertainment; healthcare and assistive technologies; affective interfaces; etc.