Sciweavers

240 search results - page 5 / 48
» A Geometric Approach for Regularization of the Data Term in ...
Sort
View
SIGGRAPH
2010
ACM
13 years 12 months ago
Feature-aligned T-meshes
High-order and regularly sampled surface representations are more efficient and compact than general meshes and considerably simplify many geometric modeling and processing algor...
Ashish Myles, Nico Pietroni, Denis Kovacs, Denis Z...
ICCV
2007
IEEE
14 years 1 months ago
Scale-Dependent 3D Geometric Features
Three-dimensional geometric data play fundamental roles in many computer vision applications. However, their scale-dependent nature, i.e. the relative variation in the spatial ext...
John Novatnack, Ko Nishino
NIPS
1994
13 years 8 months ago
From Data Distributions to Regularization in Invariant Learning
Ideally pattern recognition machines provide constant output when the inputs are transformed under a group G of desired invariances. These invariances can be achieved by enhancing...
Todd K. Leen
ICCV
2009
IEEE
15 years 14 days ago
Structure- and Motion-adaptive Regularization for High Accuracy Optic Flow
The accurate estimation of motion in image sequences is of central importance to numerous computer vision applications. Most competitive algorithms compute flow fields by minimi...
Andreas Wedel, Daniel Cremers, Thomas Pock, Horst ...
ICDM
2010
IEEE
109views Data Mining» more  ICDM 2010»
13 years 5 months ago
Term Filtering with Bounded Error
Abstract--In this paper, we consider a novel problem referred to as term filtering with bounded error to reduce the term (feature) space by eliminating terms without (or with bound...
Zi Yang, Wei Li, Jie Tang, Juanzi Li