—As it is true for human perception that we gather information from different sources in natural and multi-modality forms, learning from multi-modalities has become an effective ...
Abstract Text documents usually embody visually oriented meta-information in the form of complex visual structures, such as tables. The semantics involved in such objects result in...
Objects linking with many other objects in an information network may imply various semantic relationships. Uncovering such knowledge is essential for role discovery, data cleanin...
Chi Wang, Jiawei Han, Qi Li, Xiang Li, Wen-Pin Lin...
We reduce JavaScript to a core calculus structured as a small-step operational semantics. We present several peculiarities of the language and show that our calculus models them. W...
In this paper we describe integrated multimedia processing for Video Scout, a system that segments and indexes TV programs according to their audio, visual, and transcript informa...
Radu S. Jasinschi, Nevenka Dimitrova, Thomas McGee...