In this paper, we present a learning approach to the scenario template task of information extraction, where information filling one template could come from multiple sentences. ...
Determining the occurrence of an event is fundamental to developing systems that can observe and react to them. Often, this determination is based on collecting video and/or audio...
Dmitry N. Zotkin, Ramani Duraiswami, Larry S. Davi...
High dynamic range (HDR) imaging has become a powerful tool in computer graphics, and is being applied to scenarios like simulation of different film responses, motion blur, and i...
Michael Goesele, Wolfgang Heidrich, Hans-Peter Sei...
We study a number of open issues in spectral clustering: (i) Selecting the appropriate scale of analysis, (ii) Handling multi-scale data, (iii) Clustering with irregular backgroun...
Most recent research of scalable inductive learning on very large dataset, decision tree construction in particular, focuses on eliminating memory constraints and reducing the num...