Sciweavers

6762 search results - page 1053 / 1353
» Multiple drafts model
Sort
View
ICCV
2005
IEEE
15 years 17 days ago
Integration of Conditionally Dependent Object Features for Robust Figure/Background Segmentation
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and p...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
ICCV
2003
IEEE
15 years 17 days ago
Automatically Labeling Video Data Using Multi-class Active Learning
Labeling video data is an essential prerequisite for many vision applications that depend on training data, such as visual information retrieval, object recognition, and human act...
Rong Yan, Jie Yang, Alexander G. Hauptmann
ICCV
2001
IEEE
15 years 17 days ago
BRDF/BTF Measurement Device
Capturing surface appearance is important for a large number of applications. Appearance of real world surfaces is dif?cult to model as it varies with the direction of illuminatio...
Kristin J. Dana
ICCV
2001
IEEE
15 years 17 days ago
Flux Maximizing Geometric Flows
Several geometric active contour models have been proposed for segmentation in computer vision. The essential idea is to evolve a curve (in 2D) or a surface (in 3D) under constrai...
Alexander Vasilevskiy, Kaleem Siddiqi
ECCV
2008
Springer
15 years 16 days ago
Learning to Localize Objects with Structured Output Regression
Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to...
Matthew B. Blaschko, Christoph H. Lampert
« Prev « First page 1053 / 1353 Last » Next »