INVESTIGADORES
SANCHEZ Jorge Adrian
congresos y reuniones científicas
Título:
XRCE's Participation in Wikipedia Retrieval, Medical Image Modality Classication and Ad-hoc Retrieval Tasks of ImageCLEF 2010
Autor/es:
STÉPHANE CLINCHANT, GABRIELA CSURKA, JULIEN AH-PINE, GUILLAUME JACQUET, FLORENT PERRONNIN, JORGE SÁNCHEZ, AND KEYVAN MINOUKADEH
Reunión:
Workshop; Working Notes for the CLEF 2010 Workshop; 2010
Resumen:
This year, XRCE participated in three main tasks of ImageCLEF 2010. The Visual Concept Detection and Annotation Task is presented in a separate paper. In this working note, we rather focus on our participation in the Wikipedia Retrieval Task and in two sub-tasks of the Medical Retrieval Task (Image Modality Classication and Ad-hoc Image Retrieval). We investigated mono-modal (textual and visual) and multi-modal retrieval and classication systems. For representing text weused either standard language model or a power law (log-logistic or smoothed power law) distribution-based information retrieval model. For representing images, we used Fisher Vectors improved by power and L2 normalizations and a spatial pyramid representation. With theses representations and simple linear classiers we achieved excellent image modality classication both using mono-modal and combined textual and visual information. Concerning the retrieval performances, text based runs performed very well, but visual-only retrieval performances were in general poor showing that even state-of-the art image representations are insuficient to address these tasksaccurately. However, we have shown that despite poor visual retrieval results, multi-modal runs that combine both visual and textual retrieval scores, can outperform mono-modal systems as long as the information fusion is done appropriately. As a conclusion we can say that our participation in these tasks was successful, as the proposed systems obtained leading positions both in retrieval and modality classicationand for each type of run: text, image or mixed.