Sciweavers

518 search results - page 18 / 104
» Object correspondence as a machine learning problem
Sort
View
ICEIS
2010
IEEE
14 years 11 months ago
Pattern Recognition as a Human Centered non-Euclidean Problem
Regularities in the world are human defined. Patterns in the observed phenomena are there because we define and recognize them as such. Automatic pattern recognition tries to bridg...
Robert P. W. Duin
ICRA
2010
IEEE
144views Robotics» more  ICRA 2010»
15 years 11 days ago
Learning to grasp objects with multiple contact points
— We consider the problem of grasping novel objects and its application to cleaning a desk. A recent successful approach applies machine learning to learn one grasp point in an i...
Quoc V. Le, David Kamm, A. F. Kara, Andrew Y. Ng
118
Voted
ICCV
2005
IEEE
15 years 7 months ago
Object Detection in Aerial Imagery Based on Enhanced Semi-Supervised Learning
Object detection in aerial imagery has been well studied in computer vision for years. However, given the complexity of large variations of the appearance of the object and the ba...
Jian Yao, Zhongfei (Mark) Zhang
117
Voted
CIKM
2004
Springer
15 years 7 months ago
Hierarchical document categorization with support vector machines
Automatically categorizing documents into pre-defined topic hierarchies or taxonomies is a crucial step in knowledge and content management. Standard machine learning techniques ...
Lijuan Cai, Thomas Hofmann
CVPR
2005
IEEE
16 years 3 months ago
A Sparse Support Vector Machine Approach to Region-Based Image Categorization
Automatic image categorization using low-level features is a challenging research topic in computer vision. In this paper, we formulate the image categorization problem as a multi...
Jinbo Bi, Yixin Chen, James Ze Wang