CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
The performance of image retrieval with SVM active learning is known to be poor when started with few labelled images only. In this paper, the problem is solved by incorporating t...
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
When performing subspace modelling of data using Principal Component Analysis (PCA) it may be desirable to constrain certain directions to be more meaningful in the context of the...
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
This paper presents an algebro-geometric solution to the problem of segmenting an unknown number of subspaces of unknown and varying dimensions from sample data points. We represen...
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
We present a method for extracting dense features from stereo and motion sequences. Our dense feature is defined symmetrically with respect to both images, and it is extracted dur...
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or nonGaussian functions, leading to analytically intractable inference. ...
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
Monitoring activities using video data is an important surveillance problem. A special scenario is to learn the pattern of normal activities and detect abnormal events from a very...
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
We propose an efficient online real-time solution for singlecamera 3?D tracking of rigid objects that can handle large camera displacements, drastic aspect changes, and partial oc...
CVPR
2003
IEEE
15 years 3 days ago
2003
IEEE
We question the role that large scale filter banks have traditionally played in texture classification. It is demonstrated that textures can be classified using the joint distribu...