CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
We present an efficient probabilistic method for identity recognition in personal photo albums. Personal photos are usually taken under uncontrolled conditions ? the captured face...
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
Smoothly bent paper-like surfaces are developable. They are however difficult to minimally parameterize since the number of meaningful parameters is intrinsically dependent on the...
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
Markov Random Field, or MRF, models are a powerful tool for modeling images. While much progress has been made in algorithms for inference in MRFs, learning the parameters of an M...
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
The estimation of head pose angle from face images is an integral component of face recognition systems, human computer interfaces and other human-centered computing applications....
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
In this paper, we address the problem of detecting pedestrians in still images. We introduce an algorithm for learning shapelet features, a set of mid?level features. These featur...
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
Image patches are fundamental elements for object modeling and recognition. However, there has not been a panoramic study of the structures of the whole ensemble of natural image ...
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
We describe a method for fully automatic object recognition and segmentation using a set of reference images to specify the appearance of each object. Our method uses a generative...
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
This poster describes our recently developed real-time projector-camera system for interaction with Chinese Inkand-Wash Cartoons. We implement a real-time interactive water simula...
CVPR
2007
IEEE
15 years 1 months ago
2007
IEEE
Traditional methods for creating classifiers have two main disadvantages. Firstly, it is time consuming to acquire, or manually annotate, the training collection. Secondly, the da...