Sciweavers

1185 search results - page 35 / 237
» Bayesian Structure from Motion
Sort
View
CVPR
2006
IEEE
16 years 2 months ago
3D People Tracking with Gaussian Process Dynamical Models
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
Raquel Urtasun, David J. Fleet, Pascal Fua
99
Voted
FGR
2004
IEEE
150views Biometrics» more  FGR 2004»
15 years 4 months ago
Automated Gesture Segmentation From Dance Sequences
Complex human motion (e.g. dance) sequences are typically analyzed by segmenting them into shorter motion sequences, called gestures. However, this segmentation process is subject...
Kanav Kahol, Priyamvada Tripathi, Sethuraman Panch...
129
Voted
AFPAC
2000
Springer
252views Mathematics» more  AFPAC 2000»
15 years 5 months ago
On the Geometric Structure of Spatio-temporal Patterns
The structure of hypersurfaces corresponding to different spatio-temporal patterns is considered, and in particular representations based on geometrical invariants, such as the Ri...
Erhardt Barth, Mario Ferraro
ECCV
2000
Springer
16 years 2 months ago
Multibody Structure and Motion: 3-D Reconstruction of Independently Moving Objects
Abstract. This paper extends the recovery of structure and motion to image sequences with several independently moving objects. The motion, structure, and camera calibration are al...
Andrew W. Fitzgibbon, Andrew Zisserman
AI
2002
Springer
15 years 16 days ago
Learning Bayesian networks from data: An information-theory based approach
This paper provides algorithms that use an information-theoretic analysis to learn Bayesian network structures from data. Based on our three-phase learning framework, we develop e...
Jie Cheng, Russell Greiner, Jonathan Kelly, David ...