260 search results - page 18 / 52 » Unsupervised Learning of Human Motion Models |
MVA
2007
14 years 11 months ago
2007
A novel scheme is proposed for achieving motion segmentation in low-frame rate videos, with application to temporal super resolution. Probabilistic generative models are commonly ...
ICIP
2005
IEEE
15 years 3 months ago
2005
IEEE
This paper describes a new algorithm for the recognition of human activities. These activities are modelled using banks of switched dynamical models, each of which is tailored to ...
NIPS
2008
14 years 11 months ago
2008
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...
79
Voted
ICPR
2010
IEEE
15 years 1 days ago
2010
IEEE
—A novel non-linear dimensionality reduction method, called Temporal Laplacian Eigenmaps, is introduced to process efficiently time series data. In this embedded-based approach,...
ICIP
2006
IEEE
15 years 11 months ago
2006
IEEE
We propose a novel unsupervised learning algorithm to extract the layout of an image by learning latent object-related aspects. Unlike traditional image segmentation algorithms th...