43 search results - page 1 / 9 » Learning non-redundant codebooks for classifying complex obj... |
ICML
2009
IEEE
14 years 12 months ago
2009
IEEE
Codebook-based representations are widely employed in the classification of complex objects such as images and documents. Most previous codebook-based methods construct a single c...
ACCV
2007
Springer
14 years 5 months ago
2007
Springer
This paper presents a method for classifying the direction of movement and for segmenting objects simultaneously using features of space-time patches. Our approach uses vector quan...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
Most modern computer vision systems for high-level
tasks, such as image classification, object recognition and
segmentation, are based on learning algorithms that are
able to se...
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
Scalability of object detectors with respect to the number of classes is a very important issue for applications where many object classes need to be detected. While combining sin...
CVPR
2010
IEEE
14 years 7 months ago
2010
IEEE
The traditional SPM approach based on bag-of-features (BoF) must use nonlinear classifiers to achieve good image classification performance. This paper presents a simple but effec...