Research Interests

My research addresses the need for an efficient, effective and interactive access into large-scale image collections. In many cases the data of different modalities are inter-related, as for example photos and annotations in photo-sharing repositories, pictures and captions in news web-sites or x-ray scans and reports in medical databases, and I am investigating retrieval approaches that are capable of exploiting such inter-relationships. My PhD thesis director is Dr. François Fleuret.

Keywords: multimedia information retrieval, multimodal relevance feedback, statistical machine learning

Research proposal: Multimodal Relevance Feedback for Interactive Image Retrieval

Presentation 1: Query-Free Interactive Image Retrieval Based on Visual and Textual Features

Presentation 2: Query-Free Interactive Image Retrieval — Exploration/Exploitation Trade-Off

Demo application: interactive image retrieval (http://imr.idiap.ch)