Combining information extraction systems yields significantly higher quality resources than each system in isolation. In this paper, we generalize such a mixing of sources and fea...
Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a ...
In this paper, we describe a method for automatic creation of a knowledge source for text generation using information extraction over the Internet. We present a prototype system ...
Existing feature extraction methods explore either global statistical or local geometric information underlying the data. In this paper, we propose a general framework to learn fea...
Shuang-Hong Yang, Hongyuan Zha, Shaohua Kevin Zhou...
Much existing research on blogs focused on posts only, ignoring their comments. Our user study conducted on summarizing blog posts, however, showed that reading comments does chan...