Sciweavers

5230 search results - page 710 / 1046
» Engineering of Computer Vision Algorithms Using Evolutionary...
Sort
View
GECCO
2010
Springer
187views Optimization» more  GECCO 2010»
15 years 8 months ago
The maximum hypervolume set yields near-optimal approximation
In order to allow a comparison of (otherwise incomparable) sets, many evolutionary multiobjective optimizers use indicator functions to guide the search and to evaluate the perfor...
Karl Bringmann, Tobias Friedrich
CVPR
2005
IEEE
16 years 6 months ago
Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement
We develop an object classification method that can learn a novel class from a single training example. In this method, experience with already learned classes is used to facilita...
Evgeniy Bart, Shimon Ullman
JMLR
2012
13 years 6 months ago
Metric and Kernel Learning Using a Linear Transformation
Metric and kernel learning arise in several machine learning applications. However, most existing metric learning algorithms are limited to learning metrics over low-dimensional d...
Prateek Jain, Brian Kulis, Jason V. Davis, Inderji...
MIR
2004
ACM
154views Multimedia» more  MIR 2004»
15 years 9 months ago
Fast and robust short video clip search using an index structure
In this paper, we present an index structure-based method to fast and robustly search short video clips in large video collections. First we temporally segment a given long video ...
Junsong Yuan, Ling-Yu Duan, Qi Tian, Changsheng Xu
EMMCVPR
2005
Springer
15 years 9 months ago
Stereo for Slanted Surfaces: First Order Disparities and Normal Consistency
Traditional stereo algorithms either explicitly use the frontal parallel plane assumption by only considering position (zero-order) disparity when computing similarity measures of ...
Gang Li, Steven W. Zucker