Call for Participation in the Placing Task (Geotag Prediction for Videos)
MediaEval 2011 Benchmark Evaluation
MediaEval 2011 is offering a "Placing Task" involving automatic prediction of location (geotags) for a
set of Flickr videos based on textual tags and visual features.
Groups interested in participating can sign up by 31 May 2011 at http://www.multimediaeval.org/
The data set contains a set of geotagged
Flickr videos and the metadata for geotagged Flickr images. We also provide a set of basic visual features
extracted for all images and for keyframes from the videos. Evaluation of runs submitted by participating
groups will be based on the distance between the predicted and the actual geo-coordinates. Ground truth is
supplied by the Flickr users who uploaded the videos and the images. All videos and images are shared by
their owners under a Creative Commons license.
MediaEval is a benchmarking initiative that offers tasks promoting research and innovation on
multimodal approaches to multimedia access and retrieval. MediaEval 2011 focuses on speech and language, but also
visual and social features. Participants carry out one or more of the selected tasks and submit runs
to be evaluated. Results are to be written up and presented at the MediaEval 2011 workshop, which
will be held on September 1 - 2, 2011 in Pisa, Italy, and is a satellite workshop of Interspeech 2011.
For more information on the Placing Task, visit:
or contact the organizers:
Adam Rae, Yahoo! Research ([log in to unmask])
Vanessa Murdock, Yahoo! Research ([log in to unmask])
Pavel Serdyukov, TU Delft ([log in to unmask])
MediaEval 2011 is sponsored by the PetaMedia Network of Excellence dedicated to R&D in the area of
multimedia access and retrieval.
The Placing Task is organized by EU FP7 GLOCAL: Event-based Retrieval of Networked Media.