Ruben Granados

Multimedia Information Retrieval Based on Late Semantic Fusion Approaches: Experiments on a Wikipedia Image Collection

Main goal of this work is to show the improvement of using a textual pre-filtering combined with an image re-ranking in a Multimedia Information Retrieval task. The defined three step-based retrieval processes and a well-selected combination of visual and textual techniques help the developed Multimedia Information Retrieval System to overcome the semantic gap in a given query. In the paper, five different late semantic fusion approaches are discussed and experimented in a realistic scenario for multimedia retrieval like the one provided by the publicly available ImageCLEF Wikipedia Collection.

Some results using different approaches to merge visual and text-based features in CLEF'08 photo collection

This paper describes the participation of the MIRACLE team at the ImageCLEF Photographic Retrieval task of CLEF 2008. We succeeded in submitting 41 runs. Obtained results from text-based retrieval are better than content-based as previous experiments in the MIRACLE team campaigns [5, 6] using different software. Our main aim was to experiment with several merging approaches to fuse text-based retrieval and content-based retrieval results, and it happened that we improve the text-based baseline when applying one of the three merging algorithms, although visual results are lower than textual ones.

Enrichment of named entities for image photo retrieval

This paper describes and discusses an approach to extract and exploit enriched Named Entities for Image Photo Retrieval. The enrichment of Named Entities is inspired by the concept of definite description. The approach is evaluated using the imageCLEF-08 testset for the photo retrieval task held at Cross-Language Evaluation Forum in 2008. We are particularly interested in testing and discuss whether and how linguistic techniques such as the one presented here can be of benefit for an ad-hoc photo retrieval task. More specifically, results show an improvement in precision when Named Entities are contained in the text although for an overall improvement a better integration of these techniques in a general approach to photo retrieval is needed.