Sciweavers

911 search results - page 80 / 183
» Registration-Based Segmentation Using the Information Bottle...
Sort
View
IJCV
2002
141views more  IJCV 2002»
13 years 9 months ago
Spatio-Temporal Stereo Using Multi-Resolution Subdivision Surfaces
We present a method to automatically extract spatio-temporal descriptions of moving objects from synchronized and calibrated multi-view sequences. The object is modeled by a time-...
Jan Neumann, Yiannis Aloimonos
ACIVS
2007
Springer
14 years 4 months ago
Model-Based Image Segmentation for Multi-view Human Gesture Analysis
Multi-camera networks bring in potentials for a variety of vision-based applications through provisioning of rich visual information. In this paper a method of image segmentation f...
Chen Wu, Hamid K. Aghajan
ICCV
2011
IEEE
12 years 10 months ago
Informative Feature Selection for Object Recognition via Sparse PCA
Bag-of-words (BoW) methods are a popular class of object recognition methods that use image features (e.g., SIFT) to form visual dictionaries and subsequent histogram vectors to r...
Nikhil Naikal, Allen Y. Yang, S. Shankar Sastry
IPCV
2008
13 years 11 months ago
Robust Hough-Based Symbol Recognition Using Knowledge-Based Hierarchical Neural Networks
Abstract - A robust method for symbol recognition is presented that utilizes a compact signature based on a modified Hough Transform (HT) and knowledge-based hierarchical neural ne...
Alexander Wong, William Bishop
CLEF
2009
Springer
13 years 11 months ago
Unsupervised Word Decomposition with the Promodes Algorithm
We present Promodes, an algorithm for unsupervised word decomposition, which is based on a probabilistic generative model. The model considers segment boundaries as hidden variable...
Sebastian Spiegler, Bruno Golénia, Peter A....