Sciweavers

ICCV
2005
IEEE
15 years 1 months ago
An Expectation Maximization Approach to the Synergy between Image Segmentation and Object Categorization
In this work we deal with the problem of modelling and exploiting the interaction between the processes of image segmentation and object categorization. We propose a novel framewo...
Iasonas Kokkinos, Petros Maragos
ICCV
2005
IEEE
15 years 1 months ago
Deformation Invariant Image Matching
We propose a novel framework to build descriptors of local intensity that are invariant to general deformations. In this framework, an image is embedded as a 2D surface in 3D spac...
Haibin Ling, David W. Jacobs
ICCV
2005
IEEE
15 years 1 months ago
Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...
Zhuowen Tu
ICCV
2005
IEEE
15 years 1 months ago
Passive Photometric Stereo from Motion
We introduce an iterative algorithm for shape reconstruction from multiple images of a moving (Lambertian) object illuminated by distant (and possibly time varying) lighting. Star...
Jongwoo Lim, Jeffrey Ho, Ming-Hsuan Yang, David J....
ICCV
2005
IEEE
15 years 1 months ago
Dynamic Measurement Clustering to Aid Real Time Tracking
Many parameter estimation problems admit divide and conquer or partitioning techniques in order to reduce a highdimensional task into several reduced-dimension problems. These tec...
Christopher Kemp, Tom Drummond
ICCV
2005
IEEE
15 years 1 months ago
Consistent Surface Color for Texturing Large Objects in Outdoor Scenes
Color appearance of an object is significantly influenced by the color of the illumination. When the illumination color changes, the color appearance of the object will change acc...
Rei Kawakami, Katsushi Ikeuchi, Robby T. Tan
ICCV
2005
IEEE
15 years 1 months ago
Globally Optimal Estimates for Geometric Reconstruction Problems
We introduce a framework for computing statistically optimal estimates of geometric reconstruction problems. While traditional algorithms often suffer from either local minima or ...
Fredrik Kahl, Didier Henrion
ICCV
2005
IEEE
15 years 1 months ago
Creating Efficient Codebooks for Visual Recognition
Visual codebook based quantization of robust appearance descriptors extracted from local image patches is an effective means of capturing image statistics for texture analysis and...
Bill Triggs, Frédéric Jurie
ICCV
2005
IEEE
15 years 1 months ago
Layered Active Appearance Models
Active appearance models (AAMs) provide a framework for modeling the joint shape and texture of an image. An AAM is a compact representation of both factors in a conditionally lin...
Eagle Jones, Stefano Soatto
ICCV
2005
IEEE
15 years 1 months ago
Detection of Concentric Circles for Camera Calibration
The geometry of plane-based calibration methods is well understood, but some user interaction is often needed in practice for feature detection. This paper presents a fully automa...
Guang Jiang, Long Quan