Sciweavers

417 search results - page 3 / 84
» Dataset Issues in Object Recognition
Sort
View
ICCV
2009
IEEE
13 years 4 months ago
Incremental Multiple Kernel Learning for object recognition
A good training dataset, representative of the test images expected in a given application, is critical for ensuring good performance of a visual categorization system. Obtaining ...
Aniruddha Kembhavi, Behjat Siddiquie, Roland Miezi...
CVPR
2010
IEEE
14 years 2 months ago
Scene Classification and Detection with a Quasi-exhausitve Dataset
Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which...
Jianxiong Xiao, James Hays, Krista Ehinger, Antoni...
ICDAR
2005
IEEE
14 years 19 days ago
UPX: A New XML Representation for Annotated Datasets of Online Handwriting Data
This paper introduces our efforts to create UPX, an XML-based successor to the venerable UNIPEN format for the representation of annotated datasets of online handwriting data. In ...
Mudit Agrawal, Kalika Bali, Sriganesh Madhvanath, ...
IFIP12
2010
13 years 5 months ago
Rule Learning with Negation: Issues Regarding Effectiveness
: An investigation of rule learning processes that allow the inclusion of negated features is described. The objective is to establish whether the use of negation in inductive rule...
Stephanie Chua, Frans Coenen, Grant Malcolm
ICPR
2008
IEEE
14 years 1 months ago
Novel image feature alphabets for object recognition
Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alphabets for use in obje...
Martin Lillholm, Lewis D. Griffin