Sciweavers

313 search results - page 33 / 63
» Pose estimation and tracking using multivariate regression
Sort
View
PCM
2004
Springer
168views Multimedia» more  PCM 2004»
15 years 3 months ago
Approximating Inference on Complex Motion Models Using Multi-model Particle Filter
Abstract. Due to its great ability of conquering clutters, which is especially useful for high-dimensional tracking problems, particle filter becomes popular in the visual trackin...
Jianyu Wang, Debin Zhao, Shiguang Shan, Wen Gao
TIT
2010
118views Education» more  TIT 2010»
14 years 4 months ago
Joint sampling distribution between actual and estimated classification errors for linear discriminant analysis
Error estimation must be used to find the accuracy of a designed classifier, an issue that is critical in biomarker discovery for disease diagnosis and prognosis in genomics and p...
Amin Zollanvari, Ulisses Braga-Neto, Edward R. Dou...
ISMAR
2002
IEEE
15 years 2 months ago
Tracking with Omni-Directional Vision for Outdoor AR Systems
Most pose (3D position and 3D orientation) tracking methods using vision require a priori knowledge about the environment and correspondences between 3D environment features and 2...
Jong Weon Lee, Suya You, Ulrich Neumann
NIPS
2007
14 years 11 months ago
People Tracking with the Laplacian Eigenmaps Latent Variable Model
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
Zhengdong Lu, Miguel Á. Carreira-Perpi&ntil...
ICPR
2006
IEEE
15 years 11 months ago
Classifiers for Motion
In this paper we present a unsupervised learning based approach for sub-pixel motion estimation. The novelty of this work is the learning based method itself which tries to learn ...
Mithun Das Gupta, Nemanja Petrovic, ShyamSundar Ra...