Context in Search and Browsing of Photograph

Wednesday, October 5, 2005 - 17:30
TH 331
Andreas Paepcke , Stanford University

I will describe some experimental systems we prototyped for exploiting context in the searching and browsing of photographs. These systems include wide-area label sharing, the identification of significant photographic events through tim e and place clustering, and the automated support for otherwise manual face identity annotation in collections of photographs. The primary sources of context are the tim e and the place when photographs were taken. We assume for the purpose of this work that cameras and camera cell phones will location stamp photos in the near future. From this raw data we reconstruct the weather, sunset data and similar context, which in turn are the foundation for our 'context metadata constraint' browser (PhotoCompas), which I will introduce briefly. After describing this existing work I will show three mockups of user interfaces we are exploring for letting users visually construct geographic queries through person ali zed abstractions of geographic layouts, rather than through standard maps. This latter portion is highly speculative and hopefully invites discussion.


Dr. Andreas Paepcke is a senior research scientist and director of the Digital Library Project at Stanford University . His interests include user interfaces for small devices, novel Web search facilities, and browsing facilities for digital artifacts that are difficult to index. With his group of students he has designed and implemented WebBase, an experimental storage system for Web contents. His work on small devices has focused on novel methods for summarizing and transforming Web pages, and on browsing images on small devices. Dr. Paepcke has served on numerous program committees, including a position as Vice Program Chair, heading the World-Wide Web Conference's 'Browsers and User Interfaces' program track. He was a member on several National Science Foundation proposal evaluation panels. Dr. Paepcke received BS and MS degrees in applied mathematics from Harvard University , and a Ph.D. in Computer Science from the University of Karlsruhe, Germany. Previously, he worked as a researcher at Hewlett-Packard Laboratory, and as a research consultant at Xerox PARC.