—Network cameras, extensively used in video surveillance, often allow pan-tilt-zoom functionality and are also subject to wind load and mount vibrations, thus causing video frame...
Learning from streams of evolving and unbounded data is an important problem, for example in visual surveillance or internet scale data. For such large and evolving real-world data...
Chen Change Loy, Timothy M. Hospedales, Tao Xiang,...
This state-of-the-art report focuses on real-time image correction techniques that enable projector-camera systems to display images onto screens that are not optimized for projec...
Oliver Bimber, Daisuke Iwai, Gordon Wetzstein, Ans...
When classifying high-dimensional sequence data, traditional methods (e.g., HMMs, CRFs) may require large amounts of training data to avoid overfitting. In such cases dimensional...
This paper outlines a method to dynamically replace portals with textures in a cell-partitioned model. The rendering complexity is reduced to the geometry of the current cell thus...