18 search results - page 2 / 4 » Exploiting High Dimensional Video Features Using Layered Gau... |
CRV
2009
IEEE
13 years 11 months ago
2009
IEEE
In this paper we argue that gestures based on nonaccidental motion features can be reliably detected amongst unconstrained background motion. Specifically, we demonstrate that hu...
ACCV
2010
Springer
12 years 12 months ago
2010
Springer
Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D pose. Learning such multi-modal models ...
ICIP
2007
IEEE
14 years 6 months ago
2007
IEEE
Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...
PCM
2001
Springer
13 years 9 months ago
2001
Springer
A practical method for creating a high dimensional index structure that adapts to the data distribution and scales well with the database size, is presented. Typical media descrip...
NOLISP
2005
Springer
13 years 10 months ago
2005
Springer
The best performing systems in the area of automatic speaker recognition have focused on using short-term, low-level acoustic information, such as sepstral features. Recently, vari...