Sciweavers

690 search results - page 103 / 138
» Training of Classifiers Using Virtual Samples Only
Sort
View
IUI
2011
ACM
12 years 10 months ago
Protractor3D: a closed-form solution to rotation-invariant 3D gestures
Protractor 3D is a gesture recognizer that extends the 2D touch screen gesture recognizer Protractor [8] to 3D gestures. It inherits many of Protractor’s desirable properties, s...
Sven G. Kratz, Michael Rohs
CVPR
2009
IEEE
1385views Computer Vision» more  CVPR 2009»
15 years 9 days ago
Distance Transform Templates for Object Detection and Pose Estimation
We propose a new approach for detecting low textured planar objects and estimating their 3D pose. Standard matching and pose estimation techniques often depend on texture and fe...
Stefan Holzer, Stefan Hinterstoisser, Slobodan Ili...
ECCV
2008
Springer
14 years 9 months ago
Weakly Supervised Object Localization with Stable Segmentations
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
EPIA
2005
Springer
14 years 1 months ago
Automatic Detection of Meddies Through Texture Analysis of Sea Surface Temperature Maps
Abstract. A new machine learning approach is presented for automatic detection of Mediterranean water eddies from sea surface temperature maps of the Atlantic Ocean. A pre-processi...
Marco Castellani, Nuno C. Marques
ECCV
2008
Springer
13 years 9 months ago
Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning
Abstract. Successful multi-target tracking requires locating the targets and labeling their identities. This mission becomes significantly more challenging when many targets freque...
Xuan Song, Jinshi Cui, Hongbin Zha, Huijing Zhao