Abstract. We investigate the extent to which eye movements in natural dynamic scenes can be predicted with a simple model of bottom-up saliency, which learns on different visual re...
Eleonora Vig, Michael Dorr, Thomas Martinetz, Erha...
Automatic generation of taxonomies can be useful for a wide area of applications. In our application scenario a topical hierarchy should be constructed reasonably fast from a large...
Communication between humans deeply relies on the capability of expressing and recognizing feelings. For this reason, research on human-machine interaction needs to focus on the re...
Bayesian networks are an attractive modeling tool for human sensing, as they combine an intuitive graphical representation with ef?cient algorithms for inference and learning. Ear...
Tanzeem Choudhury, James M. Rehg, Vladimir Pavlovi...
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...