Motivation: With users' growing willingness to share personal activity information, the eventual acceptance of social multimedia, including video and audio recordings of casual interactions, is inevitable. To unlock the potential value, we need to develop methods for searching such records. This task will support such research.
Use Scenario: A new member has joined an organization or social group that has a small archive of conversations among its members. He starts to listen, looking for any information that can help him better understand, participate in, enjoy, find friends in, and succeed in this group. As he listens to the archive (perhaps at random, perhaps based on some social tags, perhaps based on an initial keyword search) he finds something of interest, and wants to find more like it, across the entire archive.
He marks what he found as a region of interest and requests more like it. The system comes back with a set of ``jump-in'' points, places in the archive to which he could jump and start listening/watching with the expectation of finding something similar.
Task Specification: Given a short second audio/video region of interest, return an ordered list of regions similar to it, where similarity is based on the perceptions of human searchers.