CMTech is a research group in Computer Vision & Human-Computer Interaction focused on human behavior understanding and interaction with the world. Human behavior understanding implies the analysis of different cues related with human non-verbal communication. One of the goals of CMTech is to allow computers to be able to understand these cues using Computer Vision and machine learning. CMTech deals with 3 main challenging tasks involving human body and hand pose inference and emotional analysis using facial expressions. These technologies provide solutions in different applications such as postural correction, understanding of sign languages or affective based human-computer interaction. In HCI, the other goal of CMTech explores the possibilities of Full-Body Interaction based on current Embodied Cognition theories in areas such as Learning, Play and Special Needs. This research is undertaken from the standpoint of Interaction Design, focusing our attention mainly on interaction for children and using non-invasive technologies such as those mentioned above.