Multimodal Image Retrieval over a Large Database

We introduce a new multimodal retrieval technique which combines query reformulation and visual image reranking in order to deal with results sparsity and imprecision, respectively. Textual queries are reformulated using Wikipedia knowledge and results are then reordered using a k-NN based reranking method. We compare textual and multimodal retrieval and show that introducing visual reranking results in a significant improvement of performance.

• Type: Journal
• Year: 2009
• Where: CLEF
• Authors: Débora Myoupo, Adrian Popescu, Hervé Le Borgne, Pierre-Alain Moëllic
• Keywords: CLEF 2009, Information Technology, Multimodal Retrieval, Multimodal Retrieval Technique, Query Reformulation