Media Informatics and Content Analysis

We are working on movies to automatically extract a variety of information. In the demo video, you'll see a clip from the movie Good Deeds, where we detect characters' faces, identify their gender (notice the color of the bounding box), detect whether they are speaking or not (a dot appears when a person speaks), and even recognize one speaker from another.
Our work involves independent and joint processing of audio, visual and text information, and developing computational models to quantify and predict emotion and other quantities related to the impact of media to our personal and social life. Starting with structure databases like movies, we plan to extend our analysis to tv shows, youtube, social media, etc.

About Us

Welcome to the SAIL Media Informatics and Content Analysis (MICA) group.
At the Signal Analysis and Interpretation Laboratory (SAIL), we conduct research on a wide variety of media related tasks which focus on human-centered applications. Our emphasis is on speech, video, music, text and multimodal information processing.
MICA's research applications and systems development concentrate on domains with direct societal relevance ranging from automated movie content analysis, understanding gender roles to gathering informatics on human interactions from speech and body gestures.