Inductive databases (IDBs) have been proposed to afford the problem of knowledge discovery from huge databases. With an IDB the user/analyst performs a set of very different operat...
The temporal segmentation of a video into shots is a fundamental prerequisite for video retrieval. There are two types of shot boundaries: abrupt shot changes (“cuts”) and grad...
Optimal Component Analysis (OCA) is a linear method for feature extraction and dimension reduction. It has been widely used in many applications such as face and object recognitio...
This paper proposes a novel hierarchical learning strategy to deal with the data sparseness problem in relation extraction by modeling the commonality among related classes. For e...
Anticipating the availability of large questionanswer datasets, we propose a principled, datadriven Instance-Based approach to Question Answering. Most question answering systems ...