Sciweavers

683 search results - page 95 / 137
» Improving object classification using semantic attributes
Sort
View
SOFTWARE
2002
13 years 7 months ago
Temporal Probabilistic Concepts from Heterogeneous Data Sequences
We consider the problem of characterisation of sequences of heterogeneous symbolic data that arise from a common underlying temporal pattern. The data, which are subject to impreci...
Sally I. McClean, Bryan W. Scotney, Fiona Palmer
CVPR
2008
IEEE
14 years 10 months ago
Semi-supervised boosting using visual similarity learning
The required amount of labeled training data for object detection and classification is a major drawback of current methods. Combining labeled and unlabeled data via semisupervise...
Christian Leistner, Helmut Grabner, Horst Bischof
ICIP
2009
IEEE
14 years 9 months ago
Parking Space Detection From Video By Augmenting Training Dataset
Auto parking techniques are attracting more attention these days. In this paper, we develop an image-based method to estimate the depth contour in parking areas. Our algorithm is ...
ICML
2000
IEEE
14 years 8 months ago
Discovering Test Set Regularities in Relational Domains
Machine learning typically involves discovering regularities in a training set, then applying these learned regularities to classify objects in a test set. In this paper we presen...
Seán Slattery, Tom M. Mitchell
ICC
2007
IEEE
166views Communications» more  ICC 2007»
14 years 2 months ago
Dynamic Optimization of Secure Mobile Sensor Networks: A Genetic Algorithm
— We propose a reduced-complexity genetic algorithm for secure and dynamic deployment of resource constrained multi-hop mobile sensor networks. Mobility and security are relative...
Rahul Khanna, Huaping Liu, Hsiao-Hwa Chen