Sciweavers

483 search results - page 65 / 97
» Accurate and Efficient Face Recognition from Video
Sort
View
CVPR
2009
IEEE
15 years 3 months ago
Max-Margin Hidden Conditional Random Fields for Human Action Recognition
We present a new method for classification with structured latent variables. Our model is formulated using the max-margin formalism in the discriminative learning literature. We...
Yang Wang 0003, Greg Mori
PKDD
2010
Springer
179views Data Mining» more  PKDD 2010»
13 years 6 months ago
Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-Like Exploration
Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achi...
Tobias Jung, Peter Stone
ICCV
2009
IEEE
13 years 6 months ago
Modeling 3D human poses from uncalibrated monocular images
This paper introduces an efficient algorithm that reconstructs 3D human poses as well as camera parameters from a small number of 2D point correspondences obtained from uncalibrat...
Xiaolin K. Wei, Jinxiang Chai
JMM2
2007
92views more  JMM2 2007»
13 years 8 months ago
Camera Control and Multimedia Interaction using Individual Object Recognition
Abstract— Currently, most of the automated, computervision assisted camera control policies are based on human events, such as the speaker gesture and position changes. In additi...
Richard Y. D. Xu, Jesse S. Jin
PAMI
2010
238views more  PAMI 2010»
13 years 6 months ago
Tracking Motion, Deformation, and Texture Using Conditionally Gaussian Processes
—We present a generative model and inference algorithm for 3D nonrigid object tracking. The model, which we call G-flow, enables the joint inference of 3D position, orientation, ...
Tim K. Marks, John R. Hershey, Javier R. Movellan