In this paper, we exploit the problem of inferring images’ semantic concepts from community-contributed images and their associated noisy tags. To infer the concepts more accura...
This paper presents an interactive image segmentation framework which is ultra-fast and accurate. Our framework, termed "CO3", consists of three components: COupled repr...
Background: Today it is common to apply multiple potentially conflicting data sources to a given phylogenetic problem. At the same time, several different inference techniques are...
We consider the problem of learning to rank relevant and novel documents so as to directly maximize a performance metric called Expected Global Utility (EGU), which has several de...
Abstract—WiFi-enabled buses and stops may form the backbone of a metropolitan delay tolerant network, that exploits nearby communications, temporary storage at stops, and predict...
Utku Acer, Paolo Giaccone, David Hay, Giovanni Neg...