The acceleration of rhythm of everyday life requires efficiency and flexibility in daily routines. The real expectations and needs of people concerning intelligent home devices sh...
Pictorial structure (PS) models are extensively used for part-based recognition of scenes, people, animals and multi-part objects. To achieve tractability, the structure and param...
Traditional Markov network structure learning algorithms perform a search for globally useful features. However, these algorithms are often slow and prone to finding local optima d...
Active learning has been proven a reliable strategy to reduce manual efforts in training data labeling. Such strategies incorporate the user as oracle: the classifier selects the m...
There is an ongoing explosion of interactive Internet applications. By nature, these applications require responsive clientserver data exchange and lossless, in-order delivery. In...