Visual mining of multimedia data for social and behavioral studies

With advances in computing techniques, a large amount of high-resolution high-quality multimedia data (video and audio, etc.) has been collected in research laboratories in various scientific disciplines, particularly in social and behavioral studies. How to automatically and effectively discover new knowledge from rich multimedia data poses a compelling challenge since state-of-the-art data mining techniques can most often only search and extract pre-defined patterns or knowledge from complex heterogeneous data. In light of this, our approach is to take advantages of both the power of human perception system and the power of computational algorithms. More specifically, we propose an approach that allows scientists to use data mining as a first pass, and then forms a closed loop of visual analysis of current results followed by more data mining work inspired by visualization, the results of which can be in turn visualized and lead to the next round of visual exploration and analysis. In this way, new insights and hypotheses gleaned from the raw data and the current level of analysis can contribute to further analysis. As a first step toward this goal, we implement a visualization system with three critical components: (1) A smooth interface between visualization and data mining. The new analysis results can be automatically loaded into our visualization tool. (2) A flexible tool to explore and query temporal data derived from raw multimedia data. We represent temporal data into two forms - continuous variables and event variables. We have developed various ways to visualize both temporal correlations and statistics of multiple variables with the same type, and conditional and high-order statistics between continuous and event variables. (3) A seamless interface between raw multimedia data and derived data. Our visualization tool allows users to explore, compare, and analyze multi-stream derived variables and simultaneously switch to access raw multimedia data. We demonstrate various functions in our visualization program using a set of multimedia data including video, audio and motion tracking data.