Sciweavers

605 search results - page 103 / 121
» Improving Generalization Performance in Co-Evolutionary Lear...
Sort
View
177
Voted
CVPR
2004
IEEE
16 years 5 months ago
3D Human Pose from Silhouettes by Relevance Vector Regression
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pr...
Ankur Agarwal, Bill Triggs
108
Voted
CVPR
2010
IEEE
15 years 12 months ago
Building and Using a Semantivisual Image Hierarchy
A semantically meaningful image hierarchy can ease the human effort in organizing thousands and millions of pictures (e.g., personal albums), and help to improve performance of en...
Li-Jia Li, Chong Wang, Yongwhan Lim, David Blei, L...
HRI
2009
ACM
15 years 10 months ago
How to approach humans?: strategies for social robots to initiate interaction
This paper proposes a model of approach behavior with which a robot can initiate conversation with people who are walking. We developed the model by learning from the failures in ...
Satoru Satake, Takayuki Kanda, Dylan F. Glas, Mich...
131
Voted
MCS
2009
Springer
15 years 10 months ago
Recoding Error-Correcting Output Codes
Abstract. One of the most widely applied techniques to deal with multiclass categorization problems is the pairwise voting procedure. Recently, this classical approach has been emb...
Sergio Escalera, Oriol Pujol, Petia Radeva
119
Voted
ICCV
2007
IEEE
15 years 10 months ago
Multilinear Projection for Appearance-Based Recognition in the Tensor Framework
Numerical multilinear (tensor) algebra is a principled mathematical approach to disentangling and explicitly and parsimoniously representing the essential factors or modes of imag...
M. Alex O. Vasilescu, Demetri Terzopoulos