Sciweavers

566 search results - page 91 / 114
» OCR with No Shape Training
Sort
View
ECCV
2008
Springer
14 years 10 months ago
Learning Two-View Stereo Matching
We propose a graph-based semi-supervised symmetric matching framework that performs dense matching between two uncalibrated wide-baseline images by exploiting the results of sparse...
Jianxiong Xiao, Jingni Chen, Dit-Yan Yeung, Long Q...
ECCV
2004
Springer
14 years 10 months ago
A Bayesian Framework for Multi-cue 3D Object Tracking
This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
Jan Giebel, Dariu Gavrila, Christoph Schnörr
ECCV
2006
Springer
14 years 10 months ago
Learning Compositional Categorization Models
Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
Björn Ommer, Joachim M. Buhmann
ICPR
2006
IEEE
14 years 9 months ago
Detecting Coarticulation in Sign Language using Conditional Random Fields
Coarticulation is one of the important factors that makes automatic sign language recognition a hard problem. Unlike in speech recognition, coarticulation effects in sign language...
Ruiduo Yang, Sudeep Sarkar
ICPR
2006
IEEE
14 years 9 months ago
Automatic Texture Synthesis for Face Recognition from Single Views
One possible solution for pose- and illuminationinvariant face recognition is to employ appearancebased approaches, which rely greatly on correct facial textures. However, existin...
Maylor K. H. Leung, Xiaozheng Zhang, Yongsheng Gao