Seamless capture and discovery for corporate memory

Daniel Billsus, Laurent Denoue, David Hilbert,
     FX Palo Alto Laboratory, Inc.

Seminar on People, Computers, and Design

In a landmark article, over a half century ago, Vannevar Bush envisioned a “Memory Extender” device which he dubbed the “memex”. Bush’s ideas anticipated and inspired numerous breakthroughs, including hypertext, the Internet, the World Wide Web, and Wikipedia. However, despite these triumphs, the memex has failed to live up to its potential in corporate settings. One reason is that corporate users often don’t have sufficient time or incentives to contribute to a corporate memory or to explore others’ contributions. At FXPAL, we are investigating ways to automatically create and retrieve useful corporate memories without any added burden on anyone. In this talk we discuss ProjectorBox—a smart appliance for automatic presentation capture—and PAL Bar—a system for proactively retrieving contextually relevant corporate memories.

Despite a glut of presentation capture technologies, useful information passes through projectors everyday and is lost. ProjectorBox seamlessly captures high-resolution slide images, text, and audio by intercepting the video signal sent from laptops to projectors. We have explored applications in corporate memory, e-learning and real-time presentation enhancement.

PAL Bar is a contextual retrieval system for proactive resource discovery, connecting users to relevant documents, presentations and people. In its latest instantiation, PAL Bar provides access to seamlessly captured content, such as ProjectorBox presentations, leading to an end-to-end corporate memory system for seamless information capture and discovery.

Daniel Billsus is a senior research scientist at FX Palo Alto Laboratory. His research focuses on intelligent information access, personalization and knowledge management technologies. Dr. Billsus currently leads FXPAL's “Information Systems” group – a team of researchers who investigate novel approaches to corporate knowledge management, text mining and collective intelligence. Before joining FXPAL, he was Chief Technology Officer at AdaptiveInfo, a personalization software provider he co-founded in 1999. He received a Ph.D. in information and computer science from the University of California, Irvine.

Laurent Denoue is a senior research scientist at FX Palo Alto Laboratory. His research interests span user interface design, document processing and social computing. Prior to FXPAL, he received his Ph.D. from the University of Savoie, France, where he designed a new Web annotation tool for web browsers (YAWAS) and devised new methods for classifying web pages into a personalized hierarchy. At FXPAL, he continued his work on annotation systems in the XLibris project for electronic books. He also worked on Shared Text Input, a novel collaborative application for taking notes on PDAs in the classroom. He also worked on the PlasmaPoster project, a tool that allows organizations to share informal content. He recently created ProjectorBox.

David Hilbert is a senior research scientist at FX Palo Alto Laboratory. His research interests lie in the design and evaluation of practical interactive, collaborative, and ubiquitous computing applications. He has contributed to the creation and improvement of numerous interactive systems at FXPAL, NASA’s Jet Propulsion Laboratory, and Microsoft. He received a PhD in information and computer science from the University of California, Irvine. He is a member of IEEE, ACM, and Phi Beta Kappa Society.

View this talk on line at CS547 on Stanford OnLine

Titles and abstracts for previous years are available by year and by speaker.