Abstract. We propose an online learning algorithm to tackle the problem of learning under limited computational resources in a teacher-student scenario, over multiple visual cues. ...
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Abstract. We present ModHel’X, an approach to multi-formalism modeling which addresses two important issues in this field: (a) providing support for the specification of the se...
d abstract] Robert Krauthgamer ∗ IBM Almaden James R. Lee † Institute for Advanced Study We initiate the study of approximate algorithms on negatively curved spaces. These spa...
Abstract. We propose a new saturation-based symbolic state-space generation algorithm for finite discrete-state systems. Based on the structure of the high-level model specificat...