A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
Surveillance systems that operate continuously generate large volumes of data. One such system is described here, continuously tracking and storing observations taken from multiple...
The paper describes a lexicon driven approach for word recognition on handwritten documents using Conditional Random Fields(CRFs). CRFs are discriminative models and do not make a...
Shravya Shetty, Harish Srinivasan, Sargur N. Sriha...
We address corpus building situations, where complete annotations to the whole corpus is time consuming and unrealistic. Thus, annotation is done only on crucial part of sentences...
Yuta Tsuboi, Hisashi Kashima, Shinsuke Mori, Hirok...
While conditional random fields (CRFs) have been applied successfully in a variety of domains, their training remains a challenging task. In this paper, we introduce a novel trai...
Lin Liao, Tanzeem Choudhury, Dieter Fox, Henry A. ...