"The 2014 Retrieving Diverse Social Images Task". PRA Lab first ranked at "MediaEval 2014 Workshop".
During the MediaEval 2014 Workshop that took place in Barcelona, on 16-17 October 2014, the team “PRa-MM2014” composed by researchers of PRA Lab-University of Cagliari and University of Trento, partecipated to a competition called “The 2014 Retrieving Diverse Social Images Task”.
The system developed by Duc-Tien Dang-Nguyen and designed with the collaboration of Giorgio Giacinto, Luca Piras (PRA Lab) and Francesco De Natale, Giulia Boato (University of Trento), won the competition.
The “Diverse Social Images Task” addresses the problem of result diversification in social photo retrieval.
From the abstract of the competition: We use a tourist use case where a person tries to find more information about a place she is potentially visiting. The person has only a vague idea about the location, e.g., knowing the name of the location. She uses the name to learn additional information about the location from the Internet, for instance by visiting a Wikipedia page, e.g., getting a photo, the geographical position of the place and basic descriptions. Before deciding whether this location suits her needs, the person is interested in getting a more complete visual description of the place.
The participating systems are expected, given a ranked list of location photos retrieved from Flickr using text information, to refine the results by providing a set of images that are in the same time relevant, e.g., depict partially or entirely the target location, and provide a diversified summary, e.g., around 50 images that depict different views of the location at different times of the day/year and under different weather conditions, creative views, etc. Initial results are typically noisy and redundant.