Abstract - A robust method for symbol recognition is presented that utilizes a compact signature based on a modified Hough Transform (HT) and knowledge-based hierarchical neural ne...
We address the automatic recovery of complete 3-D object models from video streams. Usually, complete 3-D models are built by fusing several depth maps, each computed from a small...
How different are two images when viewed by a human observer? Such knowledge is needed in many situations including when one has to judge the degree to which a graphics representa...
David J. Tolhurst, Caterina Ripamonti, C. Alejandr...
This two-day workshop examines the ways that on-line communities create and refine their shared resources, including both the formal and observable artifacts (documents, chats, th...
We study the problem of topic segmentation of manually transcribed speech in order to facilitate information extraction from dialogs. Our approach is based on a combination of mul...