HOWARD D. WACTLAR
Alumni Research Professor, Robotics, Computer Science
www

My current research interests are in information retrieval systems, multimedia, speech/image/natural language understanding and distributed systems. My emphasis in multidisciplinary projects has led to my current large project, The Informedia Digital Video Library, which integrates several CS areas.

The Informedia Digital Video Library. Vast collections of video and audio recordings which have captured events of the last century remain a largely untapped resource of historical and scientific value. Increasingly, such libraries are becoming available on the Internet. The Informedia Digital Video Library project at Carnegie Mellon University has pioneered new approaches for automated video and audio indexing, navigation, visualization, search and retrieval and embedded them in a system for use in education, information and entertainment environments. Initiated in 1994 as one of six Digital Library Initiative (DLI) projects funded jointly by NSF, DARPA and NASA, Informedia is the only one focused on the video medium.

The Informedia system provides full-content search and retrieval of current and past TV and radio news and documentary broadcasts. The system implements a fully automated process to enable daily content capture, information extraction and storage in on-line archives by applying artificial intelligence and advanced systems technology. The current library consists of more than 1,500 hours (one terabyte) of digitized daily news captured over the last two years, and documentaries produced for public television and government agencies. This prototype database allows for rapid retrieval of individual video paragraphs which satisfy an arbitrary spoken or typed subject area query based on the words in the soundtrack, closed-captioning or text overlaid on the screen. There is also a capability for matching of similar faces and images.

Our newest phase of research continues the fundamental goal of enabling for video all the functionality and capability existing for textual information retrieval, while leveraging its temporal and visual qualities for richer information delivery. To this end, Informedia-II establishes an era focused for the user as we introduce new paradigms for video information access and understanding. We aggregate and integrate video content on-demand to enable summarization and visualization that provides responses to queries in a useful broader context, perhaps with historic or geographic perspectives.

Diverse technologies and disciplines applied and integrated within Informedia include:

• Speech understanding for automatically derived transcripts and spoken queries
• Image understanding for video paragraphing (segmentation) and similarity matching
• Natural language for processing transcripts and queries
• HCI for creating novel user interfaces for video display, manipulation, and reuse
• Network authentication and billing for controlled access
• Data architectures for network retrieval-on-demand
• User studies for validation and assessment

Additional research efforts underway apply Informedia technology to the domains of education, health care, defense intelligence and the coordination and understanding of human activity. Informedia also has international digital library collaborations in Europe and Asia.