Track description

This is the second round for this track. We have significantly incremented the number of images and classes, adding a new "no-event" class. As a result, for this track more than 28000 images are labeled with the objective of performing automatic cultural event recognition from 100 categories in still images. These images belongs to 99 different cultural events and one non-class. This is the first dataset on cultural events from all around the globe. The Cultural Event Recognition challenge aims to investigate the performance of recognition methods based on several cues like garments, human poses, objects, background, etc. To this end, the cultural event dataset contains significant variability in terms of clothes, actions, illumination, localization and context.

For each one of the 100 classes, predicting presence/absence of an example of that class in the test image.

A more detailed information is provided on the data section of the competition. 


Provided Resources

  • Scripts: With the data, the organizers provides a set of scripts to facilitate the access to the data and use the evaluation metrics. More information is provided on the data page.
  • Contact: In order to clarify any doubt or to ask general assistance, you can contact the organizers at or use the forum.



There are no news registered in