Sciweavers

482 search results - page 38 / 97
» An Effective Diagnosis Method to Support Yield Improvement
Sort
View
CVPR
2008
IEEE
14 years 10 months ago
Enforcing non-positive weights for stable support vector tracking
In this paper we demonstrate that the support vector tracking (SVT) framework first proposed by Avidan is equivalent to the canonical Lucas-Kanade (LK) algorithm with a weighted E...
Simon Lucey
SEMWEB
2010
Springer
13 years 6 months ago
Supporting Natural Language Processing with Background Knowledge: Coreference Resolution Case
Systems based on statistical and machine learning methods have been shown to be extremely effective and scalable for the analysis of large amount of textual data. However, in the r...
Volha Bryl, Claudio Giuliano, Luciano Serafini, Ka...
ICASSP
2010
IEEE
13 years 9 months ago
Non-parallel training for many-to-many eigenvoice conversion
This paper presents a novel training method of an eigenvoice Gaussian mixture model (EV-GMM) effectively using non-parallel data sets for many-to-many eigenvoice conversion, which...
Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Ki...
TREC
2003
13 years 10 months ago
Interactive Search Refinement Techniques for HARD Tasks
In our entry to the new HARD track, we have investigated two methods of interactively refining user search formulations. One method consists of asking the user to select a number ...
Olga Vechtomova, Eric Lam, Murat Karamuftuoglu
ICRA
2010
IEEE
144views Robotics» more  ICRA 2010»
13 years 7 months ago
Learning to grasp objects with multiple contact points
— We consider the problem of grasping novel objects and its application to cleaning a desk. A recent successful approach applies machine learning to learn one grasp point in an i...
Quoc V. Le, David Kamm, A. F. Kara, Andrew Y. Ng