This work evaluates a few search strategies for Arabic monolingual and cross-lingual retrieval, using the TREC Arabic corpus as the test-bed. The release by NIST in 2001 of an Ara...
Libraries have traditionally used manual image annotation for indexing and then later retrieving their image collections. However, manual image annotation is an expensive and labo...
Low-level image processing algorithms generally provide noisy features that are far from being Gaussian. Medium-level tasks such as object detection must therefore be robust to out...
Sio-Song Ieng, Jean-Philippe Tarel, Pierre Charbon...
Most image retrieval systems only allow a fragment of text or an example image as a query. Most users have more complex information needs that are not easily expressed in either of...
The success of popular algorithms such as k-means clustering or nearest neighbor searches depend on the assumption that the underlying distance functions reflect domain-specific n...