6113 search results - page 153 / 1223 » Learning Features for Tracking |
133
Voted
ISMAR
2009
IEEE
15 years 9 months ago
2009
IEEE
We propose a technique for text document tracking over a large range of viewpoints. Since the popular SIFT or SURF descriptors typically fail on such documents, our method conside...
99
Voted
ECML
2003
Springer
15 years 7 months ago
2003
Springer
Many machine learning tasks contain feature evaluation as one of its important components. This work is concerned with attribute estimation in the problems where class distribution...
136
Voted
ECCV
2006
Springer
16 years 4 months ago
2006
Springer
Abstract. In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class ...
136
Voted
SLSFS
2005
Springer
15 years 8 months ago
2005
Springer
Random projection is a simple technique that has had a number of applications in algorithm design. In the context of machine learning, it can provide insight into questions such as...
115
Voted
AIPS
2007
15 years 5 months ago
2007
In sequential decision-making problems formulated as Markov decision processes, state-value function approximation using domain features is a critical technique for scaling up the...