Sciweavers

318 search results - page 2 / 64
» Computing by observing
Sort
View
CVPR
2008
IEEE
16 years 7 months ago
Context and observation driven latent variable model for human pose estimation
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
Abhinav Gupta, Trista Chen, Francine Chen, Don Kim...
CVPR
2009
IEEE
1132views Computer Vision» more  CVPR 2009»
17 years 26 days ago
Observable Subspaces for 3D Human Motion Recovery
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. T...
Andrea Fossati (EPFL), Mathieu Salzmann (Universit...
CVPR
1997
IEEE
15 years 10 months ago
Ego-Motion Estimation Using Optical Flow Fields Observed from Multiple Cameras
In this paper, we consider a multi-camera vision system mounted on a moving object in a static threedimensional environment. By using the motion ow elds seen by all of the cameras...
An-Ting Tsao, Chiou-Shann Fuh, Yi-Ping Hung, Yong-...
CVPR
2009
IEEE
17 years 24 days ago
Co-training with Noisy Perceptual Observations
Many perception and multimedia indexing problems involve datasets that are naturally comprised of multiple streams or modalities for which supervised training data is only sparsely...
Ashish Kapoor, Chris Mario Christoudias, Raquel Ur...
CVPR
2008
IEEE
15 years 7 months ago
Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera
In this paper we investigate the challenging problem of recovering the depth layers in a scene from a single defocused observation. The problem is definitely solvable if there are...
Vinay P. Namboodiri, Subhasis Chaudhuri