CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
Study of contrast sensitivity of the human eye shows that we are more sensitive to brightness differences at low intensity levels than at high intensity levels. We apply this fact...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
A method is presented for computing the radiometric response function of a camera from a single grayscale image. While most previous techniques require a set of registered images ...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
We propose using the inner-distance between landmark points to build shape descriptors. The inner-distance is defined as the length of the shortest path between landmark points wi...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
A new class of kernels for object recognition based on local image feature representations are introduced in this paper. These kernels satisfy the Mercer condition and incorporate...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
In this paper, we described an efficient feature pursuit scheme for boosting. The proposed method is based on the infomax principle, which seeks optimal feature that achieves maxi...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
Thin plate spline (TPS) transformations have been applied to non-rigid shape matching with impressive results. However, existing methods often use a sparse set of point correspond...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
Classifying pictures into one of several semantic categories is a classical image understanding problem. In this paper, we present a stratified approach to both binary (outdoor-in...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
This paper presents a technique to learn dynamic appearance models from a small number of training frames. Under this framework, dynamic appearance is modelled as an unknown opera...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
This paper presents a novel method for reconstructing complex 3D objects with unknown topology using silhouettes extracted from image sequences. This method exploits the duality p...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
Usually, object detection is performed directly on (normalized) gray values or gray primitives like gradients or Haar-like features. In that case the learning of relationships bet...