Test collections

History

2003

2004

2005

Format of results for near-duplicate detection image track

Results should be returned as one or several XML files. Each XML file contains answers for one or several tasks.

XML must have the following structure:

<?xml version="1.0"?>
<romip:taskresult xmlns:romip="http://www.romip.ru/data/classification" collectionId="ROMIP_IMG-DUPL" trackId="img-duplicate-2010">


  <romip:run>
    <romip:systemID>Yellow</romip:systemID>
    <romip:runID>MyRunId</romip:runID>
  </romip:run>


    <resultlist>
      <cluster >
          <document docID="img00001" />
          <document docID="img00002" />
          <document docID="img05037" />
      </cluster>
      <cluster>
          <document docID="img00001" />
          <document docID="img07001" />
         ....
      </cluster>
      <cluster>
         ....
      </cluster>
      ....
    </resultlist>

    </romip:taskresult>

Tag run is descriprion of the system produced the result.

systemID - system identifier provided by ROMIP organizing commitee.
runID - run identifier to distinguish between different runs of same participant. Value is up to participant.

Tag cluster describes group of near duplicates found by participant. Every group consists of images that are treated as near-duplicates to each other: every pair of images from the group is treated as near duplicates.

To identify an image (attribute docID of document tag) correspondent identifiers from the test collection should be used.