Computer analysis of human behavior

Human behavior is complex, but not random. With advances in pattern recognition and multimedia computing, it became possible to analyze human behavior at different time-scales and at different levels of interpretation. This ability opens up enormous possibilities for multimedia and multimodal interaction, with a potential of endowing the computers with a capacity to attribute meaning to users’ attitudes, preferences, personality, social relationships, etc., as well as to understand what people are doing, the activities they have been engaged in, their routines and lifestyles. Re-defining the relationship between the computer and the interacting human, moving the computer from a passive observer role to a socially active participant role and enabling it to drive different kinds of interaction has implications across multiple domains. This talk will delineate human behavior understanding as a research field, and summarize the research of our group in this field. In particular, applications in automatic analysis of facial dynamics and human-robot