MLKD's Participation at the CLEF 2011 Photo Annotation and Concept-Based Retrieval Tasks.
Eleftherios Spyromitros-Xioufis, Konstantinos Sechidis, Grigorios Tsoumakas, Ioannis P. Vlahavas · 2011
Abstract. We participated both in the photo annotation and concept-based retrieval tasks of CLEF 2011. For the annotation task we developed visual, textual and multi-modal approaches using multi-label learning al-gorithms from the Mulan open source library. For the visual model we employed the ColorDescriptor software to extract visual features from the images using 7 descriptors and 2 detectors. For each combination of descriptor and detector a multi-label model is built using the Binary Relevance approach coupled with Random Forests as the base classifier. For the textual models we used the boolean bag-of-words representation, and applied stemming, stop words removal, and feature selection using the chi-squared-max method. The multi-label learning algorithm that yielded the best results in this case was Ensemble of Classifier Chains using Random Forests as base classifier. Our multi-modal approach was based on a hierarchical late-fusion scheme. For the concept based re-trieval task we developed two different approaches. The first one is based on the concept relevance scores produced by the system we developed for the annotation task. It is a manual approach, because for each topic we manually selected the relevant topics and manually set the strength of their contribution to the final ranking produced by a general formula that combines topic relevance scores. The second approach is based solely on the sample images provided for each query and is therefore fully au-tomated. In this approach only the textual information was used in a query-by-example framework.