Sciweavers

260 search results - page 26 / 52
» Unsupervised Learning of Human Motion Models
Sort
View
CRV
2009
IEEE
132views Robotics» more  CRV 2009»
15 years 4 months ago
Non-Accidental Features for Gesture Spotting
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...
Adam Fourney, Richard Mann
NIPS
2001
14 years 11 months ago
Natural Language Grammar Induction Using a Constituent-Context Model
This paper presents a novel approach to the unsupervised learning of syntactic analyses of natural language text. Most previous work has focused on maximizing likelihood according...
Dan Klein, Christopher D. Manning
CVPR
2008
IEEE
15 years 11 months ago
Unsupervised estimation of segmentation quality using nonnegative factorization
We propose an unsupervised method for evaluating image segmentation. Common methods are typically based on evaluating smoothness within segments and contrast between them, and the...
Roman Sandler, Michael Lindenbaum
ICCV
1999
IEEE
15 years 11 months ago
A Dynamic Bayesian Network Approach to Figure Tracking using Learned Dynamic Models
The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. However, most work on tracking and synthesizing figure motion has employed eit...
Vladimir Pavlovic, James M. Rehg, Tat-Jen Cham, Ke...
MM
2003
ACM
241views Multimedia» more  MM 2003»
15 years 2 months ago
Invariance in motion analysis of videos
In this paper, we propose an approach that retrieves motion of objects from the videos based on the dynamic time warping of view invariant characteristics. The motion is represent...
Cen Rao, Mubarak Shah, Tanveer Fathima Syeda-Mahmo...