Sciweavers

87 search results - page 7 / 18
» 3D People Tracking with Gaussian Process Dynamical Models
Sort
View
ICIP
2006
IEEE
16 years 2 months ago
Video-Based Rendering using Feature Point Evolution
1 We propose a novel video-based rendering algorithm with a single moving camera. We reconstruct a dynamic 3D model of the scene with a feature point set that "evolves" o...
Wende Zhang, Tsuhan Chen
MM
2004
ACM
277views Multimedia» more  MM 2004»
15 years 5 months ago
Avatar-mediated face tracking and lip reading for human computer interaction
Advanced human computer interaction requires automatic reading of human face in order to make the computer interact with human in the same way as human-to-human communication. We ...
Xiaozhou Wei, Lijun Yin, Zhiwei Zhu, Qiang Ji
ECCV
2008
Springer
15 years 2 months ago
Active Matching
Abstract. In the matching tasks which form an integral part of all types of tracking and geometrical vision, there are invariably priors available on the absolute and/or relative i...
Margarita Chli, Andrew J. Davison
AROBOTS
2011
14 years 7 months ago
Learning GP-BayesFilters via Gaussian process latent variable models
Abstract— GP-BayesFilters are a general framework for integrating Gaussian process prediction and observation models into Bayesian filtering techniques, including particle filt...
Jonathan Ko, Dieter Fox
101
Voted
ECCV
2002
Springer
16 years 2 months ago
Recognizing and Tracking Human Action
Human activity can be described as a sequence of 3D body postures. The traditional approach to recognition and 3D reconstruction of human activity has been to track motion in 3D, m...
Josephine Sullivan, Stefan Carlsson