Abstract. The ability to recognize human activities from sensory information is essential for developing the next generation of smart devices. Many human activity recognition tasks...
Niels Landwehr, Bernd Gutmann, Ingo Thon, Luc De R...
The automatic annotation of images presents a particularly complex problem for machine learning researchers. In this work we experiment with semantic models and multi-class learnin...
We propose an information-theoretic method for multi-phase image segmentation, in an active contour-based framework. Our approach is based on nonparametric density estimates, and ...
Alan S. Willsky, Anthony J. Yezzi, John W. Fisher ...
After a long period when networking research seemed to be focused mainly on making the existing Internet work better, interest in "clean slate" approaches to network arc...
We present a structured output prediction approach for classifying potential anti-cancer drugs. Our QSAR model takes as input a description of a molecule and predicts the activity...