This paper proposes an approach to the problem of generating metadata for composite mixed-media digital objects by appropriately combining and exploiting existing knowledge or met...
Traditional approaches to combining classifiers attempt to improve classification accuracy at the cost of increased processing. They may be viewed as providing an accuracy-speed tr...
Kumar Chellapilla, Michael Shilman, Patrice Simard
The existing methods for offline training of cascade classifiers take a greedy search to optimize individual classifiers in the cascade, leading inefficient overall performance. W...
We investigate a method to speed up the O(n3 ) labeling algorithm of Rosenfeld and Pfaltz for segmenting binary images, which is unduly complex for large images. That algorithm sea...
Describing shots through the occurrence of semantic concepts is the first step towards modeling the content of a video semantically. An important challenge is to automatically se...