Sciweavers

Share
CVPR
2000
IEEE
11 years 1 months ago
Learning in Gibbsian Fields: How Accurate and How Fast Can It Be?
?Gibbsian fields or Markov random fields are widely used in Bayesian image analysis, but learning Gibbs models is computationally expensive. The computational complexity is pronoun...
Song Chun Zhu, Xiuwen Liu
CVPR
2000
IEEE
11 years 1 months ago
Hierarchical Structure and Nonrigid Motion Recovery from 2D Monocular Views
Inferring both 3D structure and motion of nonrigid objects from monocular images is an important problem in computational vision. The challenges stem not only from the absence of ...
Lin Zhou, Chandra Kambhamettu
CVPR
2000
IEEE
11 years 1 months ago
Scene Constraints-Aided Tracking of Human Body
This paper describes a new method for tracking of a human body in 3D motion by using constraints imposed on the body from the scene. An image-based approach for tracking exclusive...
Masanobu Yamamoto, Katsutoshi Yagishita
CVPR
2000
IEEE
11 years 1 months ago
Physical Panoramic Pyramid and Noise Sensitivity in Pyramids
Multi-resolution techniques have been used in a wide range of vision applications. Unfortunately, the costly operation of building a proper pyramid strongly reduces its value as a...
Weihong Yin, Terrance E. Boult
CVPR
2000
IEEE
11 years 1 months ago
Discriminant-EM Algorithm with Application to Image Retrieval
In Proc. of IEEE Conf. on CVPR'2000, Vol.I, pp.222-227, Hilton Head Island, SC, 2000 In many vision applications, the practice of supervised learning faces several difficulti...
Ying Wu, Qi Tian, Thomas S. Huang
CVPR
2000
IEEE
11 years 1 months ago
Shape-Based 3D Surface Correspondence Using Geodesics and Local Geometry
This paper describes a new method for determining correspondence between points on pairs of surfaces based on shape using a combination of geodesic distance and surface curvature....
Yongmei Wang, Bradley S. Peterson, Lawrence H. Sta...
CVPR
2000
IEEE
11 years 1 months ago
Towards Automatic Discovery of Object Categories
We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Ou...
Markus Weber, Max Welling, Pietro Perona
CVPR
2000
IEEE
11 years 1 months ago
On the Synthesis of Dynamic Scenes from Reference Views
We consider a scene, containing many objects moving with constant velocity along straight line paths, seen from three reference viewpoints at three different times.The scene may e...
Yonatan Wexler, Amnon Shashua
CVPR
2000
IEEE
11 years 1 months ago
Shape and Motion Carving in 6D
The motion of a non-rigid scene over time imposes more constraints on its structure than those derived from images at a single time instant alone. An algorithm is presented for si...
Sundar Vedula, Simon Baker, Steven M. Seitz, Takeo...
CVPR
2000
IEEE
11 years 1 months ago
Image Segmentation by Nested Cuts
We present a new image segmentation algorithm based on graph cuts. Our main tool is separation of each pixel from a special point outside the image by a cut of a minimum cost. Suc...
Olga Veksler
books