To improve the Mandarin large vocabulary continuous speech recognition (LVCSR), a unified framework based approach is introduced to exploit multi-level linguistic knowledge. In th...
Xinhao Wang, Jiazhong Nie, Dingsheng Luo, Xihong W...
The database community is on a constant quest for better integration of data management and knowledge management. Recently, with the increasing use of ontology in various applicat...
Abstract. Consistent description and representation method of user interests are required for personalized Web applications. In this paper, we provide a formal definition and the &...
Yi Zeng, Yan Wang, Zhisheng Huang, Danica Damljano...
The objective of active recognition is to iteratively collect the next "best" measurements (e.g., camera angles or viewpoints), to maximally reduce ambiguities in recogn...
Image based rendering (IBR) consists of several steps: (i) Calibration (or ego-motion computation) of all input images. (ii) Determination of regions in the input images used to s...