Sciweavers

698 search results - page 82 / 140
» Human Motion Synthesis from 3D Video
Sort
View
MM
2003
ACM
165views Multimedia» more  MM 2003»
15 years 3 months ago
Video retrieval using spatio-temporal descriptors
This paper describes a novel methodology for implementing video search functions such as retrieval of near-duplicate videos and recognition of actions in surveillance video. Video...
Daniel DeMenthon, David S. Doermann
CVPR
2005
IEEE
15 years 12 months ago
Localization in Urban Environments: Monocular Vision Compared to a Differential GPS Sensor
In this paper we present a method for computing the localization of a mobile robot with reference to a learning video sequence. The robot is first guided on a path by a human, whi...
Eric Royer, Maxime Lhuillier, Michel Dhome, Thierr...
MM
2005
ACM
188views Multimedia» more  MM 2005»
15 years 3 months ago
Detecting group activities using rigidity of formation
Most work in human activity recognition is limited to relatively simple behaviors like sitting down, standing up or other dramatic posture changes. Very little has been achieved i...
Saad M. Khan, Mubarak Shah
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...
CVPR
2008
IEEE
15 years 12 months ago
Learning human actions via information maximization
In this paper, we present a novel approach for automatically learning a compact and yet discriminative appearance-based human action model. A video sequence is represented by a ba...
Jingen Liu, Mubarak Shah