We describe a probabilistic approach to content selection for meeting summarization. We use skipchain Conditional Random Fields (CRF) to model non-local pragmatic dependencies bet...
In this paper, we propose a learning-based method for video super-resolution. There are two main contributions of the proposed method. First, information from cameras with differe...
We extend our earlier work on deep-structured conditional random field (DCRF) and develop deep-structured hidden conditional random field (DHCRF). We investigate the use of this n...
Kernel conditional random fields (KCRFs) are introduced as a framework for discriminative modeling of graph-structured data. A representer theorem for conditional graphical models...
Conditional Random Fields (CRFs) are a state-of-the-art approach to natural language processing tasks like grapheme-tophoneme (g2p) conversion which is used to produce pronunciati...
Patrick Lehnen, Stefan Hahn, Andreas Guta, Hermann...