We propose a method to adapt an existing relation extraction system to extract new relation types with minimum supervision. Our proposed method comprises two stages: learning a lo...
We present a simple, fast, and effective method to detect defects on textured surfaces. Our method is unsupervised and contains no learning stage or information on the texture bei...
Personalization has been deemed one of the major challenges in information retrieval with a significant potential for providing better search experience to individual users. Espec...
Julia Luxenburger, Shady Elbassuoni, Gerhard Weiku...
Many common materials, including fruit, wax and human skin, are somewhat translucent. What makes an object look translucent or opaque? Here we use a recently developed computer gr...
Roland W. Fleming, Henrik Wann Jensen, Heinrich H....
We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set ...