In order to analyse surveillance video, we need to efficiently explore large datasets containing videos of walking humans. At survei llance-image resolution, the human walk (their ...
In this article we present a novel fully automatic character segmentation for camera-based images. This is a top-down approach inspired by the human visual system: the high level ...
We are trying to integrate television cooking videos with corresponding cookbooks. The cookbook has the advantage of the capability to easily browse through a cooking procedure, bu...
This paper describes features and methods for document image comparison and classification at the spatial layout level. The methods are useful for visual similarity based document...
Jianying Hu, Ramanujan S. Kashi, Gordon T. Wilfong
Partial evaluation is an optimization technique traditionally used in compilation. We have adapted this technique to the understanding of scientic application programs during t...