Show simple item record

Late fusion of compact composite descriptors for retrieval from heterogeneous image databases

dc.contributor.authorChatzichristofis, Savvas A.
dc.contributor.authorArampatzis, Avi
dc.description.abstractCompact composite descriptors (CCDs) are global image features, capturing more than one types of information at the same time in a very compact representation. Their quality has so far been evaluated in retrieval from several homogeneous databases containing images of only the type that each CCD is intended for, and has been found better than other descriptors in the literature such as the MPEG-7 descriptors. In this study, we consider heterogeneous databases and investigate query-time fusion techniques for CCDs. The results show that fusion is beneficial, even with simple score normalization and combination methods due to the compatibility of the score distributions produced by the CCDs considered. Categories and Subject Descriptors: H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval— retrieval models, search process; H.2.5 [Database Management]: Heterogeneous Databases General Terms: Measurement, Experimentation, Theoryen_UK
dc.publisherAssociation for Computing Machinery (ACM), United Statesen_UK
dc.relation.ispartofseriesProceedings of the 33rd international ACM SIGIR conference on;Research and development in information retrieval, Geneva, Switzerland — July 19 - 23, 2010
dc.relation.ispartofseriesProceeding SIGIR '10 Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval;
dc.rightsACM New York, NY, USA ©2010en_UK
dc.subjectResearch Subject Categories::TECHNOLOGYen_UK
dc.subjectImage Retrievalen_UK
dc.titleLate fusion of compact composite descriptors for retrieval from heterogeneous image databasesen_UK
dc.typeWorking Paperen_UK

Files in this item


This item appears in the following Collection(s)

Show simple item record

ACM New York, NY, USA ©2010
Except where otherwise noted, this item's license is described as ACM New York, NY, USA ©2010