Sciweavers

63 search results - page 8 / 13
» Approximating Representations for Large Numerical Databases
Sort
View
ECCV
2002
Springer
14 years 9 months ago
Implicit Probabilistic Models of Human Motion for Synthesis and Tracking
Abstract. This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Given the high dimensional nature of human motion, learning an ...
Hedvig Sidenbladh, Michael J. Black, Leonid Sigal
ICCV
2009
IEEE
15 years 20 days ago
Patch based Within-Object Classification
Advances in object detection have made it possible to collect large databases of certain objects. In this paper we exploit these datasets for within-object classification. For e...
Jania Aghajanian, Jonathan Warrell, Simon J.D. Pri...
ICIP
1999
IEEE
14 years 9 months ago
A Fast Algorithm for Rigid Structure from Image Sequences
The factorization method [1] is a feature-based approach to recover 3D rigid structure from motion. In [2], we extended their framework to recover a parametric description of the ...
Pedro M. Q. Aguiar, José M. F. Moura
JMLR
2010
156views more  JMLR 2010»
13 years 2 months ago
Collaborative Filtering on a Budget
Matrix factorization is a successful technique for building collaborative filtering systems. While it works well on a large range of problems, it is also known for requiring signi...
Alexandros Karatzoglou, Alexander J. Smola, Markus...
ICDE
2009
IEEE
176views Database» more  ICDE 2009»
14 years 9 months ago
Efficient Table Anonymization for Aggregate Query Answering
Abstract-- Privacy protection is a major concern when microdata needs to be released for ad hoc analyses. This has led to a lot of recent research in privacy goals and table anonym...
Cecilia M. Procopiuc, Divesh Srivastava