Sciweavers

1546 search results - page 28 / 310
» Computing Pose Sequences Directly from Videos
Sort
View
ECCV
2010
Springer
14 years 18 days ago
Human Attributes from 3D Pose Tracking
We show that, from the output of a simple 3D human pose tracker one can infer physical attributes (e.g., gender and weight) and aspects of mental state (e.g., happiness or sadness)...
ICRA
2009
IEEE
135views Robotics» more  ICRA 2009»
14 years 2 months ago
A nonlinear observer for 6 DOF pose estimation from inertial and bearing measurements
— This paper considers the problem of estimating pose from inertial and bearing-only vision measurements. We present a non-linear observer that evolves directly on the special Eu...
Grant Baldwin, Robert E. Mahony, Jochen Trumpf
ETRA
2006
ACM
136views Biometrics» more  ETRA 2006»
14 years 1 months ago
Computational mechanisms for gaze direction in interactive visual environments
Next-generation immersive virtual environments and video games will require virtual agents with human-like visual attention and gaze behaviors. A critical step is to devise effic...
Robert J. Peters, Laurent Itti
CVPR
2006
IEEE
14 years 1 months ago
Shape from Dynamic Texture for Planes
We propose a method for recovering the affine geometry of a dynamically textured plane from a video sequence taken by an uncalibrated, fixed, perspective camera. Some instances ...
Yaser Sheikh, Niels C. Haering, Mubarak Shah
CVPR
2000
IEEE
13 years 12 months ago
Step towards Sequence-to-Sequence Alignment
This paper presents an approach for establishing correspondencesin time and in space between two differentvideo sequences of the same dynamic scene, recorded by stationary uncalib...
Yaron Caspi, Michal Irani