Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...
Jan Moringen, Sven Wachsmuth, Sven J. Dickinson, S...
The environment around us is progressively equipped with various sensors, producing data continuously. The applications using these data face many challenges, such as data stream i...
Semantic information helps in identifying the context of a document. It will be interesting to find out how effectively this information can be used in recommending related docume...
Named Entity Recognition is a relatively well-understood NLP task, with many publicly available training resources and software for English. Other languages tend to be underserved...
Mixtures of probabilistic principal component analyzers model high-dimensional nonlinear data by combining local linear models. Each mixture component is specifically designed to...