Sciweavers

5230 search results - page 710 / 1046
» Engineering of Computer Vision Algorithms Using Evolutionary...
Sort
View
GECCO
2010
Springer
187views Optimization» more  GECCO 2010»
16 years 2 days 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 9 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 9 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»
16 years 21 days 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
16 years 24 days 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