K2: Knowledge Kaleidoscope

K2 is a framework for finding images of named entities.

With the proliferation of photo and video footage on the Web, a knowledge base would not be complete without multimodal data on individual entities like people or landmarks. While photos of celebrities are abundant on the Internet, they are much harder to retrieve for less popular entities such as notable computer scientists or regionally interesting churches. Querying the entity names in image search engines yields large candidate lists, but they often have low precision and unsatisfactory recall.

Moreover, even for more prominent targets, it is desirable to have a diverse collection of photos (e.g., from different time periods), some of which might be rare and difficult to locate using search engines. In some cases, the ambiguity of the entity name dilutes the search engine results. An example is the distinguished economist David Gale. Searching with "David Gale" yields results that are dominated by the actor Kevin Spacey who acted in the movie "The Life of David Gale" (totally unrelated to the economist).

Part of the YAGO-NAGA project at the Max-Planck Institute for Informatics in Saarbrücken/Germany.

Publications