In this study we present a client-based architecture that supports time-shift Digital-TV (DTV) features (i.e., pause, replay and fast-forward) and interactive applications. We cal...
Abstract. In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class ...
This work presents a methodology for grouping structurally similar XML documents using clustering algorithms. Modeling XML documents with tree-like structures, we face the ‘clust...
Theodore Dalamagas, Tao Cheng, Klaas-Jan Winkel, T...
This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. ...
Stereo and 3D reconstruction are used by many applications such as object modeling, facial expression studies and human motion analysis. But synchronizing multiple high frame rate ...