Feature selection is an important task in order to achieve better generalizability in high dimensional learning, and structure learning of Markov random fields (MRFs) can automat...
Prolac is a new statically-typed, object-oriented language for network protocol implementation. It is designed for readability, extensibility, and real-world implementation; most ...
Eddie Kohler, M. Frans Kaashoek, David R. Montgome...
Abstract. Sensor relocation protocols can be employed as fault tolerance approach to offset the coverage loss caused by node failures. We introduce a novel localized structure, in...
We present a method to automatically extract spatio-temporal descriptions of moving objects from synchronized and calibrated multi-view sequences. The object is modeled by a time-...
We present a unified model for face detection, pose estimation, and landmark estimation in real-world, cluttered images. Our model is based on a mixtures of trees with a shared p...