David Lillis: SIFT


SIFT (Segmented Information Fusion Techniques) was an SFI-funded project based in UCD. It was aimed at applying fusion techniques in the area of Information Retrieval.

The Project

Specifically, SIFT looked at improving the existing ProbFuse and SlideFuse algorithms (see publications) with a view to entering international competitions such as TREC. It also examined the impact of diversity in data fusion tasks, drawing from experiences in the area of machine learning.

As part of our research, we entered the TREC Web Track in 2009, 2010 and 2011. We also entered the ImageCLEF Fusion Task in 2010.