Sciweavers

381 search results - page 51 / 77
» Using multiple segmentations for image auto-annotation
Sort
View
ICIP
1999
IEEE
13 years 12 months ago
Motion Segmentation with Level Sets
Segmentation of motion in an image sequence is one of the most challenging problems in image processing, while at the same time one that finds numerous applications. To date, a wea...
Abdol-Reza Mansouri, Janusz Konrad
CVPR
2003
IEEE
1110views Computer Vision» more  CVPR 2003»
14 years 9 months ago
Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach
Producing an accurate motion flow field is very difficult at motion boundaries. We present a novel, noniterative approach for segmentation from image motion, based on two voting p...
Gérard G. Medioni, Mircea Nicolescu
CBMS
2004
IEEE
13 years 11 months ago
Partial Shape Matching of Spine X-Ray Shapes Using Dynamic Programming
The osteophyte shows only on some particular locations on the vertebra. This indicates that other locations on the vertebra shape contain that are not of interest hinder the spine...
Xiaoqian Xu, D. J. Lee, Sameer Antani, L. Rodney L...
CVPR
2009
IEEE
15 years 2 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...
ICCV
2011
IEEE
12 years 7 months ago
Kinecting the dots: Particle Based Scene Flow from depth sensors
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
Simon Hadfield, Richard Bowden