Large public displays have become a regular conceptual element in many shops and businesses, where they advertise products or highlight upcoming events. In our work, we are interes...
Florian Alt, Nemanja Memarovic, Ivan Elhart, Domin...
When multiple data sources are available for clustering, an a priori data integration process is usually required. This process may be costly and may not lead to good clusterings,...
Elisa Boari de Lima, Raquel Cardoso de Melo Minard...
We study how to best use crowdsourced relevance judgments learning to rank [1, 7]. We integrate two lines of prior work: unreliable crowd-based binary annotation for binary classi...
In this paper, we show how to reconstruct both 3D shape and 2D texture of a class of surfaces from a single perspective image. We consider the so-called the generalized cylindrica...
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...