Sciweavers

29 search results - page 6 / 6
» Detecting and Reading Text in Natural Scenes
Sort
View
ICCSA
2003
Springer
14 years 22 days ago
Information Extraction to Generate Visual Simulations of Car Accidents from Written Descriptions
This paper describes a system to create animated 3D scenes of car accidents from written reports. The text-to-scene conversion process consists of two stages. An information extrac...
Pierre Nugues, Sylvain Dupuy, Arjan Egges
WWW
2010
ACM
14 years 2 months ago
Shout out: integrating news and reader comments
A useful approach for enabling computers to automatically create new content is utilizing the text, media, and information already present on the World Wide Web. The newly created...
Lisa M. Gandy, Nathan D. Nichols, Kristian J. Hamm...
ETRA
2008
ACM
235views Biometrics» more  ETRA 2008»
13 years 9 months ago
Using semantic content as cues for better scanpath prediction
Under natural viewing conditions, human observers use shifts in gaze to allocate processing resources to subsets of the visual input. There are many computational models that try ...
Moran Cerf, E. Paxon Frady, Christof Koch
ICIP
2001
IEEE
14 years 9 months ago
Anti-geometric diffusion for adaptive thresholding and segmentation
In this paper, we present a novel adaptive thresholding technique based upon an anisotropic diffusionmodel, whichmay be referred to as the anti-geometric heat flow. In contrast to...
Siddharth Manay, Anthony J. Yezzi