Sciweavers

662 search results - page 40 / 133
» Method of Motion Data Processing Based on Manifold Learning
Sort
View
HIS
2004
13 years 9 months ago
Adaptive Boosting with Leader based Learners for Classification of Large Handwritten Data
Boosting is a general method for improving the accuracy of a learning algorithm. AdaBoost, short form for Adaptive Boosting method, consists of repeated use of a weak or a base le...
T. Ravindra Babu, M. Narasimha Murty, Vijay K. Agr...
DAGM
2006
Springer
14 years 4 days ago
Near Real-Time Motion Segmentation Using Graph Cuts
We present a new approach to integrated motion estimation and segmentation by combining methods from discrete and continuous optimization. The velocity of each of a set of regions ...
Thomas Schoenemann, Daniel Cremers
NIPS
1998
13 years 9 months ago
Example-Based Image Synthesis of Articulated Figures
We present a method for learning complex appearance mappings, such as occur with images of articulated objects. Traditional interpolation networks fail on this case since appearan...
Trevor Darrell
ICASSP
2010
IEEE
13 years 8 months ago
Speech modeling based on committee-based active learning
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
Yuzu Hamanaka, Koichi Shinoda, Sadaoki Furui, Tada...
CVPR
2012
IEEE
11 years 11 months ago
Finite Element based sequential Bayesian Non-Rigid Structure from Motion
Navier’s equations modelling linear elastic solid deformations are embedded within an Extended Kalman Filter (EKF) to compute a sequential Bayesian estimate for the Non-Rigid St...
Antonio Agudo, Begoña Calvo, J. M. M. Monti...