Sciweavers

437 search results - page 45 / 88
» Models and the locus of their truth
Sort
View
ICMCS
2000
IEEE
110views Multimedia» more  ICMCS 2000»
15 years 1 months ago
Video Scene Segmentation using Video and Audio Features
In this paper we present a novel algorithm for video scene segmentation. We model a scene as a semantically consistent chunk of audio-visual data. Central to the segmentation fram...
Hari Sundaram, Shih-Fu Chang
CVPR
2009
IEEE
1216views Computer Vision» more  CVPR 2009»
16 years 4 months ago
Marked Point Processes for Crowd Counting
A Bayesian marked point process (MPP) model is developed to detect and count people in crowded scenes. The model couples a spatial stochastic process governing number and placem...
Robert T. Collins, Weina Ge

Publication
375views
15 years 3 months ago
 Dynamic View Expansion for Minimally Invasive Surgery using Simultaneous Localization And Mapping
Navigation during Minimally Invasive Surgery (MIS) has recognized difficulties due to limited field-of-view, off-axis visualization and loss of direct 3D vision. This can cause ...
Peter Mountney and Guang-Zhong Yang
TOG
2012
187views Communications» more  TOG 2012»
13 years 6 days ago
CrossShade: shading concept sketches using cross-section curves
We facilitate the creation of 3D-looking shaded production drawings from concept sketches. The key to our approach is a class of commonly used construction curves known as cross-s...
Cloud Shao, Adrien Bousseau, Alla Sheffer, Karan S...
ICCV
1998
IEEE
15 years 11 months ago
Sectored Snakes: Evaluating Learned-Energy Segmentations
We describe how to teach deformable models to maximize image segmentation correctness based on user-specified criteria, and we present a method for evaluating which criteria work ...
Samuel D. Fenster, John R. Kender