Sciweavers

593 search results - page 15 / 119
» Unsupervised Learning of Invariant Features Using Video
Sort
View
FGR
2000
IEEE
161views Biometrics» more  FGR 2000»
14 years 23 hour ago
Learning and Synthesizing Human Body Motion and Posture
A novel approach is presented for estimating human body posture and motion from a video sequence. Human pose is defined as the instantaneous image plane configuration of a singl...
Rómer Rosales, Stan Sclaroff
ISDA
2009
IEEE
14 years 2 months ago
Measures for Unsupervised Fuzzy-Rough Feature Selection
For supervised learning, feature selection algorithms attempt to maximise a given function of predictive accuracy. This function usually considers the ability of feature vectors t...
Neil MacParthalain, Richard Jensen
ACCV
2010
Springer
13 years 2 months ago
Learning Rare Behaviours
Abstract. We present a novel approach to detect and classify rare behaviours which are visually subtle and occur sparsely in the presence of overwhelming typical behaviours. We tre...
Jian Li, Timothy M. Hospedales, Shaogang Gong, Tao...
CIVR
2005
Springer
169views Image Analysis» more  CIVR 2005»
14 years 1 months ago
An Invariant Representation for Matching Trajectories Across Uncalibrated Video Streams
Abstract. We introduce a view–point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on...
Walter Nunziati, Stan Sclaroff, Alberto Del Bimbo
ISVC
2010
Springer
13 years 6 months ago
Bivariate Feature Localization for SIFT Assuming a Gaussian Feature Shape
In this paper, the well-known SIFT detector is extended with a bivariate feature localization. This is done by using function models that assume a Gaussian feature shape for the de...
Kai Cordes, Oliver Müller, Bodo Rosenhahn, J&...