In this paper we present a surprisingly simple yet powerful method for detecting illumination--determining which pixels are lit by different lights--in images. Our method is based...
Popular content in video sharing web sites (e.g., YouTube) is usually duplicated. Most scholars define near-duplicate video clips (NDVC) based on non-semantic features (e.g., di...
Mauro Cherubini, Rodrigo de Oliveira, Nuria Oliver
Most current image retrieval systems and commercial search engines use mainly text annotations to index and retrieve WWW images. This research explores the use of machine learning...
A fundamental part of a Computer Science degree is learning to program. Rather than starting students on a full commercial language, we favour using a dedicated "teaching lan...
This paper explores area/parallelism tradeo s in the design of distributed shared-memory (DSM) multiprocessors built out of large single-chip computing nodes. In this context, are...