The Twelfth International Conference on Multimodal Interfaces and the Seventh Workshop on Machine Learning for Multimodal Interaction will be held jointly in Beijing China during November 8-12, 2010. The main aim of ICMI-MLMI 2010 is to further scientific research within the broad field of multimodal interaction, methods, and systems, focusing on major trends and challenges, and working towards identifying a roadmap for future research and commercial success. The conference will continue to feature a single-track with keynote speakers, technical paper presentations, poster sessions, a doctoral consortium, and demonstrations of state of the art multimodal systems and concepts. The conference will be followed by workshops.

Topics of interest include, but are not limited to:

• Multimodal input and output interfaces
• Multimodal human behavior analysis
• Machine learning methods for multimodal processing
• Fusion techniques and hybrid architectures
• Processing of language and action patterns
• Gaze and vision-based interfaces
• Speech and conversational interfaces
• Pen-based interfaces
• Haptic interfaces
• Brain-computer interfaces
• Cognitive modeling of users • Multi-biometric interfaces
• Multimodal-multisensor interfaces
• Interfaces for attentive and intelligent environments
• Mobile, tangible and virtual/augmented multimodal interfaces
• Distributed/collaborative multimodal interfaces
• Tools and system infrastructure issues for designing multimodal interfaces
• Evaluation of multimodal interfaces
• AI techniques and adaptive multimodal interfaces